Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3580 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4947. Min Range: -7.4947
Max Act: 7.4947. Min Act: -0.1700
Data Index: 6647810 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4947. Min Range: -7.4947
Max Act: 7.3697. Min Act: -0.1700
Data Index: 7759979 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4947. Min Range: -7.4947
Max Act: 7.3385. Min Act: -0.1700
Data Index: 3255444 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4947. Min Range: -7.4947
Max Act: 7.2135. Min Act: -0.1700
Data Index: 508285 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4947. Min Range: -7.4947
Max Act: 7.2135. Min Act: -0.1700
Data Index: 509051 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4947. Min Range: -7.4947
Max Act: 7.1510. Min Act: -0.1700
Data Index: 4968827 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4947. Min Range: -7.4947
Max Act: 7.1197. Min Act: -0.1700
Data Index: 2408173 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4947. Min Range: -7.4947
Max Act: 7.0572. Min Act: -0.1700
Data Index: 3566352 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4947. Min Range: -7.4947
Max Act: 6.9947. Min Act: -0.1700
Data Index: 931090 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4947. Min Range: -7.4947
Max Act: 7.0260. Min Act: -0.1700
Data Index: 5299167 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4947. Min Range: -7.4947
Max Act: 6.9947. Min Act: -0.1700
Data Index: 5777370 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4947. Min Range: -7.4947
Max Act: 6.9635. Min Act: -0.1700
Data Index: 5187561 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4947. Min Range: -7.4947
Max Act: 6.9635. Min Act: -0.1700
Data Index: 7564523 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4947. Min Range: -7.4947
Max Act: 6.9322. Min Act: -0.1700
Data Index: 4683973 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4947. Min Range: -7.4947
Max Act: 6.9010. Min Act: -0.1700
Data Index: 2367283 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4947. Min Range: -7.4947
Max Act: 6.9010. Min Act: -0.1700
Data Index: 7629772 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4947. Min Range: -7.4947
Max Act: 6.9322. Min Act: -0.1700
Data Index: 2597738 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4947. Min Range: -7.4947
Max Act: 6.9010. Min Act: -0.1700
Data Index: 1208205 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4947. Min Range: -7.4947
Max Act: 6.9010. Min Act: -0.1700
Data Index: 6491761 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4947. Min Range: -7.4947
Max Act: 6.8697. Min Act: -0.1700
Data Index: 8615832 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19