Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3267 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1961. Min Range: -4.1961
Max Act: 4.1961. Min Act: -0.1700
Data Index: 2534125 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1961. Min Range: -4.1961
Max Act: 4.0710. Min Act: -0.1700
Data Index: 6487976 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1961. Min Range: -4.1961
Max Act: 3.7897. Min Act: -0.1700
Data Index: 1744397 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1961. Min Range: -4.1961
Max Act: 3.7740. Min Act: -0.1700
Data Index: 8709707 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1961. Min Range: -4.1961
Max Act: 3.7897. Min Act: -0.1700
Data Index: 8468606 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1961. Min Range: -4.1961
Max Act: 3.7427. Min Act: -0.1700
Data Index: 5846671 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1961. Min Range: -4.1961
Max Act: 3.7271. Min Act: -0.1700
Data Index: 8761256 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1961. Min Range: -4.1961
Max Act: 3.7271. Min Act: -0.1700
Data Index: 3349094 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1961. Min Range: -4.1961
Max Act: 3.7115. Min Act: -0.1700
Data Index: 3493275 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1961. Min Range: -4.1961
Max Act: 3.6958. Min Act: -0.1700
Data Index: 3221034 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1961. Min Range: -4.1961
Max Act: 3.6802. Min Act: -0.1700
Data Index: 441315 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1961. Min Range: -4.1961
Max Act: 3.6645. Min Act: -0.1700
Data Index: 3753282 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1961. Min Range: -4.1961
Max Act: 3.6645. Min Act: -0.1700
Data Index: 634221 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1961. Min Range: -4.1961
Max Act: 3.6489. Min Act: -0.1700
Data Index: 4069593 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1961. Min Range: -4.1961
Max Act: 3.6332. Min Act: -0.1700
Data Index: 2844006 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1961. Min Range: -4.1961
Max Act: 3.6332. Min Act: -0.1700
Data Index: 2633755 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1961. Min Range: -4.1961
Max Act: 3.6019. Min Act: -0.1700
Data Index: 6642783 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1961. Min Range: -4.1961
Max Act: 3.6019. Min Act: -0.1700
Data Index: 5025908 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1961. Min Range: -4.1961
Max Act: 3.6176. Min Act: -0.1700
Data Index: 6502524 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1961. Min Range: -4.1961
Max Act: 3.5863. Min Act: -0.1700
Data Index: 3159528 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19