Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2375 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3445. Min Range: -5.3445
Max Act: 5.3445. Min Act: -0.1700
Data Index: 6705176 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3445. Min Range: -5.3445
Max Act: 5.1257. Min Act: -0.1700
Data Index: 3787114 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3445. Min Range: -5.3445
Max Act: 4.9382. Min Act: -0.1700
Data Index: 3270736 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3445. Min Range: -5.3445
Max Act: 4.9382. Min Act: -0.1700
Data Index: 1019979 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3445. Min Range: -5.3445
Max Act: 4.8757. Min Act: -0.1700
Data Index: 3377748 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3445. Min Range: -5.3445
Max Act: 4.8132. Min Act: -0.1700
Data Index: 5038747 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3445. Min Range: -5.3445
Max Act: 4.8132. Min Act: -0.1700
Data Index: 4938269 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3445. Min Range: -5.3445
Max Act: 4.8132. Min Act: -0.1700
Data Index: 4520964 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3445. Min Range: -5.3445
Max Act: 4.7820. Min Act: -0.1700
Data Index: 3798617 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3445. Min Range: -5.3445
Max Act: 4.8132. Min Act: -0.1700
Data Index: 5890360 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3445. Min Range: -5.3445
Max Act: 4.7507. Min Act: -0.1700
Data Index: 7219357 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3445. Min Range: -5.3445
Max Act: 4.7507. Min Act: -0.1700
Data Index: 1858350 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3445. Min Range: -5.3445
Max Act: 4.7195. Min Act: -0.1700
Data Index: 5924793 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3445. Min Range: -5.3445
Max Act: 4.6570. Min Act: -0.1700
Data Index: 7023014 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3445. Min Range: -5.3445
Max Act: 4.6570. Min Act: -0.1700
Data Index: 8773870 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3445. Min Range: -5.3445
Max Act: 4.6570. Min Act: -0.1700
Data Index: 6125751 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3445. Min Range: -5.3445
Max Act: 4.6570. Min Act: -0.1700
Data Index: 5625443 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3445. Min Range: -5.3445
Max Act: 4.6570. Min Act: -0.1700
Data Index: 2316305 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3445. Min Range: -5.3445
Max Act: 4.6570. Min Act: -0.1700
Data Index: 559798 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3445. Min Range: -5.3445
Max Act: 4.6570. Min Act: -0.1700
Data Index: 4022475 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19