Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3963 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3759. Min Range: -1.3759
Max Act: 1.3759. Min Act: -0.1700
Data Index: 1540147 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3759. Min Range: -1.3759
Max Act: 1.3671. Min Act: -0.1699
Data Index: 5392752 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3759. Min Range: -1.3759
Max Act: 1.3494. Min Act: -0.1700
Data Index: 2351579 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3759. Min Range: -1.3759
Max Act: 1.3406. Min Act: -0.1700
Data Index: 3984547 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3759. Min Range: -1.3759
Max Act: 1.3406. Min Act: -0.1694
Data Index: 1533661 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3759. Min Range: -1.3759
Max Act: 1.3318. Min Act: -0.1699
Data Index: 8071907 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3759. Min Range: -1.3759
Max Act: 1.3406. Min Act: -0.1695
Data Index: 1871288 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3759. Min Range: -1.3759
Max Act: 1.3406. Min Act: -0.1700
Data Index: 5756462 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3759. Min Range: -1.3759
Max Act: 1.3318. Min Act: -0.1700
Data Index: 6734230 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3759. Min Range: -1.3759
Max Act: 1.3318. Min Act: -0.1700
Data Index: 5520275 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3759. Min Range: -1.3759
Max Act: 1.3230. Min Act: -0.1700
Data Index: 6543835 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3759. Min Range: -1.3759
Max Act: 1.3318. Min Act: -0.1699
Data Index: 4259073 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3759. Min Range: -1.3759
Max Act: 1.3141. Min Act: -0.1699
Data Index: 7373214 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3759. Min Range: -1.3759
Max Act: 1.3141. Min Act: -0.1700
Data Index: 1735616 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3759. Min Range: -1.3759
Max Act: 1.3230. Min Act: -0.1699
Data Index: 3856350 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3759. Min Range: -1.3759
Max Act: 1.3230. Min Act: -0.1700
Data Index: 202900 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3759. Min Range: -1.3759
Max Act: 1.3141. Min Act: -0.1700
Data Index: 8617100 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3759. Min Range: -1.3759
Max Act: 1.3141. Min Act: -0.1697
Data Index: 1213109 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3759. Min Range: -1.3759
Max Act: 1.3230. Min Act: -0.1700
Data Index: 7601986 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3759. Min Range: -1.3759
Max Act: 1.3141. Min Act: -0.1699
Data Index: 7910927 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19