Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1247 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5235. Min Range: -6.5235
Max Act: 6.5235. Min Act: -0.1700
Data Index: 8814402 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5235. Min Range: -6.5235
Max Act: 6.2422. Min Act: -0.1700
Data Index: 8153419 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5235. Min Range: -6.5235
Max Act: 6.1172. Min Act: -0.1700
Data Index: 65292 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5235. Min Range: -6.5235
Max Act: 6.0860. Min Act: -0.1700
Data Index: 4255436 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5235. Min Range: -6.5235
Max Act: 6.0547. Min Act: -0.1700
Data Index: 4921054 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5235. Min Range: -6.5235
Max Act: 6.0235. Min Act: -0.1700
Data Index: 7322088 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5235. Min Range: -6.5235
Max Act: 6.0235. Min Act: -0.1700
Data Index: 8689712 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5235. Min Range: -6.5235
Max Act: 5.9610. Min Act: -0.1700
Data Index: 6678016 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5235. Min Range: -6.5235
Max Act: 5.9922. Min Act: -0.1700
Data Index: 3407272 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5235. Min Range: -6.5235
Max Act: 5.9610. Min Act: -0.1700
Data Index: 6027285 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5235. Min Range: -6.5235
Max Act: 5.9297. Min Act: -0.1700
Data Index: 8028874 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5235. Min Range: -6.5235
Max Act: 5.9297. Min Act: -0.1700
Data Index: 2160122 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5235. Min Range: -6.5235
Max Act: 5.8985. Min Act: -0.1700
Data Index: 5708552 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5235. Min Range: -6.5235
Max Act: 5.8985. Min Act: -0.1700
Data Index: 2083140 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5235. Min Range: -6.5235
Max Act: 5.8985. Min Act: -0.1700
Data Index: 8138604 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5235. Min Range: -6.5235
Max Act: 5.8985. Min Act: -0.1700
Data Index: 6726880 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5235. Min Range: -6.5235
Max Act: 5.8985. Min Act: -0.1700
Data Index: 1921663 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5235. Min Range: -6.5235
Max Act: 5.8985. Min Act: -0.1700
Data Index: 5312554 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5235. Min Range: -6.5235
Max Act: 5.8985. Min Act: -0.1700
Data Index: 4233452 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5235. Min Range: -6.5235
Max Act: 5.8985. Min Act: -0.1700
Data Index: 6191259 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19