Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 326 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2275. Min Range: -6.2275
Max Act: 6.2275. Min Act: -0.1700
Data Index: 8003069 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2275. Min Range: -6.2275
Max Act: 5.9775. Min Act: -0.1700
Data Index: 4710017 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2275. Min Range: -6.2275
Max Act: 5.9462. Min Act: -0.1700
Data Index: 5210348 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2275. Min Range: -6.2275
Max Act: 5.8212. Min Act: -0.1700
Data Index: 4458480 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2275. Min Range: -6.2275
Max Act: 5.8212. Min Act: -0.1700
Data Index: 7090964 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2275. Min Range: -6.2275
Max Act: 5.7587. Min Act: -0.1700
Data Index: 3595065 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2275. Min Range: -6.2275
Max Act: 5.7275. Min Act: -0.1700
Data Index: 4000703 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2275. Min Range: -6.2275
Max Act: 5.6962. Min Act: -0.1700
Data Index: 1876400 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2275. Min Range: -6.2275
Max Act: 5.6337. Min Act: -0.1700
Data Index: 1916433 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2275. Min Range: -6.2275
Max Act: 5.6650. Min Act: -0.1700
Data Index: 6499044 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2275. Min Range: -6.2275
Max Act: 5.6650. Min Act: -0.1700
Data Index: 6629283 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2275. Min Range: -6.2275
Max Act: 5.6650. Min Act: -0.1700
Data Index: 5297742 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2275. Min Range: -6.2275
Max Act: 5.6337. Min Act: -0.1700
Data Index: 4721764 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2275. Min Range: -6.2275
Max Act: 5.6337. Min Act: -0.1700
Data Index: 5414407 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2275. Min Range: -6.2275
Max Act: 5.6025. Min Act: -0.1700
Data Index: 5727915 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2275. Min Range: -6.2275
Max Act: 5.5712. Min Act: -0.1700
Data Index: 4861419 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2275. Min Range: -6.2275
Max Act: 5.6025. Min Act: -0.1700
Data Index: 6675176 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2275. Min Range: -6.2275
Max Act: 5.6025. Min Act: -0.1700
Data Index: 3567028 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2275. Min Range: -6.2275
Max Act: 5.5712. Min Act: -0.1700
Data Index: 3392627 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2275. Min Range: -6.2275
Max Act: 5.6025. Min Act: -0.1700
Data Index: 2210931 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19