Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4800 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9073. Min Range: -2.9073
Max Act: 2.9073. Min Act: -0.1698
Data Index: 6610551 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9073. Min Range: -2.9073
Max Act: 2.7323. Min Act: -0.1644
Data Index: 4909324 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9073. Min Range: -2.9073
Max Act: 2.5072. Min Act: -0.1700
Data Index: 7478198 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9073. Min Range: -2.9073
Max Act: 2.4260. Min Act: -0.1700
Data Index: 4993231 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9073. Min Range: -2.9073
Max Act: 2.3934. Min Act: -0.1700
Data Index: 6610550 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9073. Min Range: -2.9073
Max Act: 2.4097. Min Act: -0.1682
Data Index: 4514350 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9073. Min Range: -2.9073
Max Act: 2.3279. Min Act: -0.1692
Data Index: 3364712 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9073. Min Range: -2.9073
Max Act: 2.2950. Min Act: -0.1698
Data Index: 8456044 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9073. Min Range: -2.9073
Max Act: 2.2620. Min Act: -0.1697
Data Index: 8425826 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9073. Min Range: -2.9073
Max Act: 2.1958. Min Act: -0.1700
Data Index: 7316531 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9073. Min Range: -2.9073
Max Act: 2.1792. Min Act: -0.1699
Data Index: 946503 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9073. Min Range: -2.9073
Max Act: 2.1709. Min Act: -0.1670
Data Index: 4400220 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9073. Min Range: -2.9073
Max Act: 2.1376. Min Act: -0.1700
Data Index: 2422159 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9073. Min Range: -2.9073
Max Act: 2.1292. Min Act: -0.1698
Data Index: 7793951 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9073. Min Range: -2.9073
Max Act: 2.1292. Min Act: -0.1700
Data Index: 3069975 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9073. Min Range: -2.9073
Max Act: 2.1292. Min Act: -0.1699
Data Index: 4993227 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9073. Min Range: -2.9073
Max Act: 2.0958. Min Act: -0.1686
Data Index: 7793952 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9073. Min Range: -2.9073
Max Act: 2.0538. Min Act: -0.1700
Data Index: 7478199 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9073. Min Range: -2.9073
Max Act: 2.0370. Min Act: -0.1700
Data Index: 8295191 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9073. Min Range: -2.9073
Max Act: 1.9694. Min Act: -0.1683
Data Index: 1467851 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19