Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3003 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6976. Min Range: -5.6976
Max Act: 5.6976. Min Act: -0.1700
Data Index: 8531762 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6976. Min Range: -5.6976
Max Act: 5.6038. Min Act: -0.1700
Data Index: 6468718 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6976. Min Range: -5.6976
Max Act: 5.3226. Min Act: -0.1700
Data Index: 4570585 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6976. Min Range: -5.6976
Max Act: 5.2913. Min Act: -0.1700
Data Index: 3377766 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6976. Min Range: -5.6976
Max Act: 5.2288. Min Act: -0.1700
Data Index: 1540414 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6976. Min Range: -5.6976
Max Act: 5.2288. Min Act: -0.1700
Data Index: 1705933 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6976. Min Range: -5.6976
Max Act: 5.1976. Min Act: -0.1700
Data Index: 4855371 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6976. Min Range: -5.6976
Max Act: 5.1663. Min Act: -0.1700
Data Index: 6386656 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6976. Min Range: -5.6976
Max Act: 5.1663. Min Act: -0.1700
Data Index: 5411441 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6976. Min Range: -5.6976
Max Act: 5.1663. Min Act: -0.1700
Data Index: 4457259 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6976. Min Range: -5.6976
Max Act: 5.1663. Min Act: -0.1700
Data Index: 7631369 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6976. Min Range: -5.6976
Max Act: 5.1663. Min Act: -0.1700
Data Index: 4469917 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6976. Min Range: -5.6976
Max Act: 5.1663. Min Act: -0.1700
Data Index: 1500872 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6976. Min Range: -5.6976
Max Act: 5.1351. Min Act: -0.1700
Data Index: 1706198 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6976. Min Range: -5.6976
Max Act: 5.1351. Min Act: -0.1700
Data Index: 5692407 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6976. Min Range: -5.6976
Max Act: 5.1038. Min Act: -0.1700
Data Index: 633797 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6976. Min Range: -5.6976
Max Act: 5.1038. Min Act: -0.1700
Data Index: 278161 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6976. Min Range: -5.6976
Max Act: 5.1038. Min Act: -0.1700
Data Index: 27079 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6976. Min Range: -5.6976
Max Act: 5.0726. Min Act: -0.1700
Data Index: 6988601 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6976. Min Range: -5.6976
Max Act: 5.0726. Min Act: -0.1700
Data Index: 2381728 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19