Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2254 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8233. Min Range: -10.8233
Max Act: 10.8233. Min Act: -0.1700
Data Index: 7039094 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8233. Min Range: -10.8233
Max Act: 10.6983. Min Act: -0.1700
Data Index: 3069588 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8233. Min Range: -10.8233
Max Act: 10.6358. Min Act: -0.1700
Data Index: 7503115 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8233. Min Range: -10.8233
Max Act: 10.6983. Min Act: -0.1700
Data Index: 4755726 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8233. Min Range: -10.8233
Max Act: 10.5733. Min Act: -0.1700
Data Index: 6165734 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8233. Min Range: -10.8233
Max Act: 10.5733. Min Act: -0.1700
Data Index: 4330180 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8233. Min Range: -10.8233
Max Act: 10.5733. Min Act: -0.1700
Data Index: 1961331 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8233. Min Range: -10.8233
Max Act: 10.5108. Min Act: -0.1700
Data Index: 3639099 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8233. Min Range: -10.8233
Max Act: 10.5108. Min Act: -0.1700
Data Index: 8454539 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8233. Min Range: -10.8233
Max Act: 10.5108. Min Act: -0.1700
Data Index: 3630726 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8233. Min Range: -10.8233
Max Act: 10.5108. Min Act: -0.1700
Data Index: 2607010 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8233. Min Range: -10.8233
Max Act: 10.4483. Min Act: -0.1700
Data Index: 1490429 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8233. Min Range: -10.8233
Max Act: 10.4483. Min Act: -0.1700
Data Index: 453712 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8233. Min Range: -10.8233
Max Act: 10.4483. Min Act: -0.1700
Data Index: 6988229 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8233. Min Range: -10.8233
Max Act: 10.3858. Min Act: -0.1700
Data Index: 1476632 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8233. Min Range: -10.8233
Max Act: 10.4483. Min Act: -0.1700
Data Index: 6933920 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8233. Min Range: -10.8233
Max Act: 10.3858. Min Act: -0.1700
Data Index: 4704354 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8233. Min Range: -10.8233
Max Act: 10.3858. Min Act: -0.1700
Data Index: 6612437 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8233. Min Range: -10.8233
Max Act: 10.3233. Min Act: -0.1700
Data Index: 4483463 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8233. Min Range: -10.8233
Max Act: 10.3858. Min Act: -0.1700
Data Index: 4617677 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19