Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1580 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0458. Min Range: -7.0458
Max Act: 7.0458. Min Act: -0.1700
Data Index: 7062311 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0458. Min Range: -7.0458
Max Act: 6.9520. Min Act: -0.1700
Data Index: 644909 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0458. Min Range: -7.0458
Max Act: 6.9208. Min Act: -0.1700
Data Index: 6654089 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0458. Min Range: -7.0458
Max Act: 6.9208. Min Act: -0.1700
Data Index: 7649610 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0458. Min Range: -7.0458
Max Act: 6.8270. Min Act: -0.1700
Data Index: 1767439 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0458. Min Range: -7.0458
Max Act: 6.7958. Min Act: -0.1700
Data Index: 3454104 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0458. Min Range: -7.0458
Max Act: 6.7958. Min Act: -0.1700
Data Index: 1352846 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0458. Min Range: -7.0458
Max Act: 6.7958. Min Act: -0.1700
Data Index: 7037568 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0458. Min Range: -7.0458
Max Act: 6.7645. Min Act: -0.1700
Data Index: 4945022 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0458. Min Range: -7.0458
Max Act: 6.7645. Min Act: -0.1700
Data Index: 5068709 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0458. Min Range: -7.0458
Max Act: 6.7645. Min Act: -0.1700
Data Index: 146768 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0458. Min Range: -7.0458
Max Act: 6.7645. Min Act: -0.1700
Data Index: 5161633 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0458. Min Range: -7.0458
Max Act: 6.7645. Min Act: -0.1700
Data Index: 3484238 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0458. Min Range: -7.0458
Max Act: 6.7645. Min Act: -0.1700
Data Index: 1111430 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0458. Min Range: -7.0458
Max Act: 6.7333. Min Act: -0.1700
Data Index: 735983 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0458. Min Range: -7.0458
Max Act: 6.7333. Min Act: -0.1700
Data Index: 5766262 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0458. Min Range: -7.0458
Max Act: 6.7333. Min Act: -0.1700
Data Index: 8205486 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0458. Min Range: -7.0458
Max Act: 6.7020. Min Act: -0.1700
Data Index: 8202389 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0458. Min Range: -7.0458
Max Act: 6.7020. Min Act: -0.1700
Data Index: 5274625 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0458. Min Range: -7.0458
Max Act: 6.7020. Min Act: -0.1700
Data Index: 348007 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19