Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3419 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1236. Min Range: -7.1236
Max Act: 7.1236. Min Act: -0.1700
Data Index: 3735654 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1236. Min Range: -7.1236
Max Act: 7.1236. Min Act: -0.1700
Data Index: 3352911 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1236. Min Range: -7.1236
Max Act: 6.9049. Min Act: -0.1700
Data Index: 5391561 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1236. Min Range: -7.1236
Max Act: 6.8424. Min Act: -0.1700
Data Index: 7846887 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1236. Min Range: -7.1236
Max Act: 6.7799. Min Act: -0.1700
Data Index: 2348954 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1236. Min Range: -7.1236
Max Act: 6.7174. Min Act: -0.1700
Data Index: 8439311 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1236. Min Range: -7.1236
Max Act: 6.7174. Min Act: -0.1700
Data Index: 8620674 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1236. Min Range: -7.1236
Max Act: 6.7174. Min Act: -0.1700
Data Index: 6519578 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1236. Min Range: -7.1236
Max Act: 6.7174. Min Act: -0.1700
Data Index: 8515357 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1236. Min Range: -7.1236
Max Act: 6.7174. Min Act: -0.1700
Data Index: 8378291 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1236. Min Range: -7.1236
Max Act: 6.6861. Min Act: -0.1700
Data Index: 4018933 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1236. Min Range: -7.1236
Max Act: 6.6861. Min Act: -0.1700
Data Index: 1127587 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1236. Min Range: -7.1236
Max Act: 6.6861. Min Act: -0.1700
Data Index: 7026730 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1236. Min Range: -7.1236
Max Act: 6.6549. Min Act: -0.1700
Data Index: 343683 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1236. Min Range: -7.1236
Max Act: 6.6549. Min Act: -0.1700
Data Index: 8724961 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1236. Min Range: -7.1236
Max Act: 6.6236. Min Act: -0.1700
Data Index: 4717389 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1236. Min Range: -7.1236
Max Act: 6.5924. Min Act: -0.1700
Data Index: 7815267 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1236. Min Range: -7.1236
Max Act: 6.6236. Min Act: -0.1700
Data Index: 8568084 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1236. Min Range: -7.1236
Max Act: 6.5924. Min Act: -0.1700
Data Index: 6672586 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1236. Min Range: -7.1236
Max Act: 6.5924. Min Act: -0.1700
Data Index: 6257671 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19