Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3492 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8268. Min Range: -6.8268
Max Act: 6.8268. Min Act: -0.1700
Data Index: 5166180 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8268. Min Range: -6.8268
Max Act: 6.5455. Min Act: -0.1700
Data Index: 5823155 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8268. Min Range: -6.8268
Max Act: 6.3893. Min Act: -0.1700
Data Index: 8362076 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8268. Min Range: -6.8268
Max Act: 6.3580. Min Act: -0.1700
Data Index: 4723123 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8268. Min Range: -6.8268
Max Act: 6.2643. Min Act: -0.1700
Data Index: 1400587 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8268. Min Range: -6.8268
Max Act: 6.2955. Min Act: -0.1700
Data Index: 7940462 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8268. Min Range: -6.8268
Max Act: 6.2955. Min Act: -0.1700
Data Index: 7603387 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8268. Min Range: -6.8268
Max Act: 6.2330. Min Act: -0.1700
Data Index: 216286 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8268. Min Range: -6.8268
Max Act: 6.2018. Min Act: -0.1700
Data Index: 4550336 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8268. Min Range: -6.8268
Max Act: 6.1705. Min Act: -0.1700
Data Index: 5676030 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8268. Min Range: -6.8268
Max Act: 6.1393. Min Act: -0.1700
Data Index: 8134147 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8268. Min Range: -6.8268
Max Act: 6.1393. Min Act: -0.1700
Data Index: 568546 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8268. Min Range: -6.8268
Max Act: 6.0768. Min Act: -0.1700
Data Index: 3672558 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8268. Min Range: -6.8268
Max Act: 6.0768. Min Act: -0.1700
Data Index: 1234721 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8268. Min Range: -6.8268
Max Act: 6.0455. Min Act: -0.1700
Data Index: 7594067 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8268. Min Range: -6.8268
Max Act: 6.0768. Min Act: -0.1700
Data Index: 8194152 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8268. Min Range: -6.8268
Max Act: 6.0143. Min Act: -0.1700
Data Index: 970473 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8268. Min Range: -6.8268
Max Act: 6.0143. Min Act: -0.1700
Data Index: 8048198 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8268. Min Range: -6.8268
Max Act: 6.0143. Min Act: -0.1700
Data Index: 4866040 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8268. Min Range: -6.8268
Max Act: 6.0143. Min Act: -0.1700
Data Index: 4186485 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19