Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3236 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6826. Min Range: -5.6826
Max Act: 5.6826. Min Act: -0.1700
Data Index: 3729970 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6826. Min Range: -5.6826
Max Act: 5.5576. Min Act: -0.1700
Data Index: 184427 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6826. Min Range: -5.6826
Max Act: 5.4638. Min Act: -0.1700
Data Index: 4434033 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6826. Min Range: -5.6826
Max Act: 5.4326. Min Act: -0.1700
Data Index: 7925310 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6826. Min Range: -5.6826
Max Act: 5.4326. Min Act: -0.1700
Data Index: 2613901 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6826. Min Range: -5.6826
Max Act: 5.3701. Min Act: -0.1700
Data Index: 6931521 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6826. Min Range: -5.6826
Max Act: 5.3701. Min Act: -0.1700
Data Index: 7692320 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6826. Min Range: -5.6826
Max Act: 5.3388. Min Act: -0.1700
Data Index: 952788 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6826. Min Range: -5.6826
Max Act: 5.3388. Min Act: -0.1700
Data Index: 3783645 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6826. Min Range: -5.6826
Max Act: 5.3388. Min Act: -0.1700
Data Index: 1758914 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6826. Min Range: -5.6826
Max Act: 5.3076. Min Act: -0.1700
Data Index: 1733818 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6826. Min Range: -5.6826
Max Act: 5.3076. Min Act: -0.1700
Data Index: 5491401 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6826. Min Range: -5.6826
Max Act: 5.3076. Min Act: -0.1700
Data Index: 2305848 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6826. Min Range: -5.6826
Max Act: 5.3076. Min Act: -0.1700
Data Index: 3499913 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6826. Min Range: -5.6826
Max Act: 5.3076. Min Act: -0.1700
Data Index: 1426373 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6826. Min Range: -5.6826
Max Act: 5.2763. Min Act: -0.1700
Data Index: 1488253 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6826. Min Range: -5.6826
Max Act: 5.2763. Min Act: -0.1700
Data Index: 4118689 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6826. Min Range: -5.6826
Max Act: 5.2763. Min Act: -0.1700
Data Index: 8576567 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6826. Min Range: -5.6826
Max Act: 5.2451. Min Act: -0.1700
Data Index: 6776870 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6826. Min Range: -5.6826
Max Act: 5.2451. Min Act: -0.1700
Data Index: 6041400 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19