Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1104 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1550. Min Range: -6.1550
Max Act: 6.1550. Min Act: -0.1698
Data Index: 7565663 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1550. Min Range: -6.1550
Max Act: 6.0925. Min Act: -0.1700
Data Index: 8254715 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1550. Min Range: -6.1550
Max Act: 5.9675. Min Act: -0.1700
Data Index: 593428 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1550. Min Range: -6.1550
Max Act: 5.9363. Min Act: -0.1700
Data Index: 4281552 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1550. Min Range: -6.1550
Max Act: 5.9050. Min Act: -0.1700
Data Index: 7565662 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1550. Min Range: -6.1550
Max Act: 5.8425. Min Act: -0.1700
Data Index: 8254714 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1550. Min Range: -6.1550
Max Act: 5.8113. Min Act: -0.1700
Data Index: 3961945 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1550. Min Range: -6.1550
Max Act: 5.8113. Min Act: -0.1700
Data Index: 1542972 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1550. Min Range: -6.1550
Max Act: 5.7488. Min Act: -0.1700
Data Index: 3890661 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1550. Min Range: -6.1550
Max Act: 5.7488. Min Act: -0.1700
Data Index: 443054 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1550. Min Range: -6.1550
Max Act: 5.6863. Min Act: -0.1700
Data Index: 5053735 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1550. Min Range: -6.1550
Max Act: 5.6550. Min Act: -0.1700
Data Index: 727113 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1550. Min Range: -6.1550
Max Act: 5.6550. Min Act: -0.1700
Data Index: 8655870 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1550. Min Range: -6.1550
Max Act: 5.6550. Min Act: -0.1700
Data Index: 2231568 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1550. Min Range: -6.1550
Max Act: 5.6238. Min Act: -0.1700
Data Index: 1128787 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1550. Min Range: -6.1550
Max Act: 5.6238. Min Act: -0.1700
Data Index: 6892079 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1550. Min Range: -6.1550
Max Act: 5.5925. Min Act: -0.1700
Data Index: 6499246 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1550. Min Range: -6.1550
Max Act: 5.5925. Min Act: -0.1700
Data Index: 6385752 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1550. Min Range: -6.1550
Max Act: 5.5925. Min Act: -0.1700
Data Index: 4017833 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1550. Min Range: -6.1550
Max Act: 5.5613. Min Act: -0.1700
Data Index: 5835969 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19