Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2250 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1674. Min Range: -2.1674
Max Act: 2.1674. Min Act: -0.1700
Data Index: 7201159 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1674. Min Range: -2.1674
Max Act: 2.0166. Min Act: -0.1700
Data Index: 7810849 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1674. Min Range: -2.1674
Max Act: 1.9828. Min Act: -0.1700
Data Index: 1063074 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1674. Min Range: -2.1674
Max Act: 1.9828. Min Act: -0.1700
Data Index: 8421082 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1674. Min Range: -2.1674
Max Act: 1.9658. Min Act: -0.1700
Data Index: 4471138 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1674. Min Range: -2.1674
Max Act: 1.9658. Min Act: -0.1700
Data Index: 2493082 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1674. Min Range: -2.1674
Max Act: 1.9489. Min Act: -0.1700
Data Index: 5055078 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1674. Min Range: -2.1674
Max Act: 1.9319. Min Act: -0.1700
Data Index: 3297104 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1674. Min Range: -2.1674
Max Act: 1.9319. Min Act: -0.1700
Data Index: 2292285 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1674. Min Range: -2.1674
Max Act: 1.9319. Min Act: -0.1700
Data Index: 3138794 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1674. Min Range: -2.1674
Max Act: 1.9319. Min Act: -0.1700
Data Index: 6463833 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1674. Min Range: -2.1674
Max Act: 1.9319. Min Act: -0.1700
Data Index: 411112 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1674. Min Range: -2.1674
Max Act: 1.9149. Min Act: -0.1700
Data Index: 8553542 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1674. Min Range: -2.1674
Max Act: 1.9149. Min Act: -0.1700
Data Index: 2653535 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1674. Min Range: -2.1674
Max Act: 1.9149. Min Act: -0.1700
Data Index: 3401002 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1674. Min Range: -2.1674
Max Act: 1.9149. Min Act: -0.1700
Data Index: 4708402 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1674. Min Range: -2.1674
Max Act: 1.9149. Min Act: -0.1700
Data Index: 5544070 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1674. Min Range: -2.1674
Max Act: 1.9149. Min Act: -0.1700
Data Index: 7118064 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1674. Min Range: -2.1674
Max Act: 1.8978. Min Act: -0.1700
Data Index: 4860371 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1674. Min Range: -2.1674
Max Act: 1.8978. Min Act: -0.1700
Data Index: 2959698 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19