Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 71 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6942. Min Range: -7.6942
Max Act: 7.6942. Min Act: -0.1700
Data Index: 3066486 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6942. Min Range: -7.6942
Max Act: 7.5692. Min Act: -0.1700
Data Index: 2211275 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6942. Min Range: -7.6942
Max Act: 7.4442. Min Act: -0.1700
Data Index: 1328554 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6942. Min Range: -7.6942
Max Act: 7.3505. Min Act: -0.1700
Data Index: 6218050 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6942. Min Range: -7.6942
Max Act: 7.2255. Min Act: -0.1700
Data Index: 5075548 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6942. Min Range: -7.6942
Max Act: 7.2255. Min Act: -0.1700
Data Index: 4775663 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6942. Min Range: -7.6942
Max Act: 7.1942. Min Act: -0.1700
Data Index: 6400792 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6942. Min Range: -7.6942
Max Act: 7.1942. Min Act: -0.1700
Data Index: 3558441 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6942. Min Range: -7.6942
Max Act: 7.1005. Min Act: -0.1700
Data Index: 5075564 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6942. Min Range: -7.6942
Max Act: 7.0692. Min Act: -0.1700
Data Index: 6430861 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6942. Min Range: -7.6942
Max Act: 6.9442. Min Act: -0.1700
Data Index: 2857323 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6942. Min Range: -7.6942
Max Act: 6.9442. Min Act: -0.1700
Data Index: 6400797 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6942. Min Range: -7.6942
Max Act: 6.9442. Min Act: -0.1700
Data Index: 8181152 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6942. Min Range: -7.6942
Max Act: 6.9130. Min Act: -0.1700
Data Index: 8107693 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6942. Min Range: -7.6942
Max Act: 6.9130. Min Act: -0.1700
Data Index: 5346244 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6942. Min Range: -7.6942
Max Act: 6.8505. Min Act: -0.1700
Data Index: 5596402 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6942. Min Range: -7.6942
Max Act: 6.8817. Min Act: -0.1700
Data Index: 4255969 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6942. Min Range: -7.6942
Max Act: 6.7880. Min Act: -0.1700
Data Index: 2857328 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6942. Min Range: -7.6942
Max Act: 6.7880. Min Act: -0.1699
Data Index: 2857322 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6942. Min Range: -7.6942
Max Act: 6.7880. Min Act: -0.1700
Data Index: 2857329 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19