Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6190 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0330. Min Range: -7.0330
Max Act: 7.0330. Min Act: -0.1700
Data Index: 1391718 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0330. Min Range: -7.0330
Max Act: 6.5955. Min Act: -0.1700
Data Index: 4849763 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0330. Min Range: -7.0330
Max Act: 6.5643. Min Act: -0.1700
Data Index: 184521 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0330. Min Range: -7.0330
Max Act: 6.4393. Min Act: -0.1700
Data Index: 3573911 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0330. Min Range: -7.0330
Max Act: 6.3768. Min Act: -0.1700
Data Index: 3355826 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0330. Min Range: -7.0330
Max Act: 6.3768. Min Act: -0.1700
Data Index: 7646715 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0330. Min Range: -7.0330
Max Act: 6.3455. Min Act: -0.1700
Data Index: 8667234 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0330. Min Range: -7.0330
Max Act: 6.2830. Min Act: -0.1700
Data Index: 6704079 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0330. Min Range: -7.0330
Max Act: 6.2830. Min Act: -0.1700
Data Index: 4348513 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0330. Min Range: -7.0330
Max Act: 6.1893. Min Act: -0.1700
Data Index: 5020786 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0330. Min Range: -7.0330
Max Act: 6.2518. Min Act: -0.1700
Data Index: 4390978 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0330. Min Range: -7.0330
Max Act: 6.1893. Min Act: -0.1700
Data Index: 6312390 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0330. Min Range: -7.0330
Max Act: 6.1580. Min Act: -0.1700
Data Index: 8370447 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0330. Min Range: -7.0330
Max Act: 6.1580. Min Act: -0.1700
Data Index: 7132130 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0330. Min Range: -7.0330
Max Act: 6.1893. Min Act: -0.1700
Data Index: 1528112 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0330. Min Range: -7.0330
Max Act: 6.1580. Min Act: -0.1700
Data Index: 3883353 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0330. Min Range: -7.0330
Max Act: 6.1268. Min Act: -0.1700
Data Index: 4831778 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0330. Min Range: -7.0330
Max Act: 6.1580. Min Act: -0.1700
Data Index: 7132128 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0330. Min Range: -7.0330
Max Act: 6.1580. Min Act: -0.1700
Data Index: 5949690 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0330. Min Range: -7.0330
Max Act: 6.1268. Min Act: -0.1700
Data Index: 3119644 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19