Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2425 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.6124. Min Act: -0.1700
Data Index: 3672931 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.5499. Min Act: -0.1700
Data Index: 6400255 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.4561. Min Act: -0.1700
Data Index: 3842518 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.4561. Min Act: -0.1700
Data Index: 2486327 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.4249. Min Act: -0.1700
Data Index: 5174720 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.3936. Min Act: -0.1700
Data Index: 6328939 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.3311. Min Act: -0.1700
Data Index: 6299200 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.2686. Min Act: -0.1700
Data Index: 6228387 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.2686. Min Act: -0.1700
Data Index: 6202049 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.2686. Min Act: -0.1700
Data Index: 4865671 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.2686. Min Act: -0.1700
Data Index: 4806225 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.2686. Min Act: -0.1700
Data Index: 3020802 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.2374. Min Act: -0.1700
Data Index: 8545153 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.1749. Min Act: -0.1700
Data Index: 6961706 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.2061. Min Act: -0.1700
Data Index: 963720 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.2061. Min Act: -0.1700
Data Index: 1335306 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.1749. Min Act: -0.1700
Data Index: 7933908 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.1749. Min Act: -0.1700
Data Index: 6142229 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.1749. Min Act: -0.1700
Data Index: 1442411 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6124. Min Range: -5.6124
Max Act: 5.1749. Min Act: -0.1700
Data Index: 2803516 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19