Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2384 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0261. Min Range: -7.0261
Max Act: 7.0261. Min Act: -0.1700
Data Index: 7138557 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.9323. Min Act: -0.1700
Data Index: 7772548 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.8386. Min Act: -0.1700
Data Index: 4891206 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.7136. Min Act: -0.1700
Data Index: 4760644 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.6823. Min Act: -0.1700
Data Index: 5162003 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.6823. Min Act: -0.1700
Data Index: 4493807 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.7136. Min Act: -0.1700
Data Index: 4642424 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.5886. Min Act: -0.1700
Data Index: 2737976 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.5573. Min Act: -0.1700
Data Index: 3882743 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.5573. Min Act: -0.1700
Data Index: 4906552 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.5261. Min Act: -0.1700
Data Index: 5496190 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.4948. Min Act: -0.1700
Data Index: 4951292 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.4323. Min Act: -0.1700
Data Index: 1465896 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.4948. Min Act: -0.1700
Data Index: 3415314 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.4948. Min Act: -0.1700
Data Index: 2010299 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.4323. Min Act: -0.1700
Data Index: 7962691 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.4323. Min Act: -0.1700
Data Index: 2974941 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.4323. Min Act: -0.1700
Data Index: 3232547 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.4011. Min Act: -0.1700
Data Index: 4865119 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.3698. Min Act: -0.1700
Data Index: 3260858 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19