Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1543 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7193. Min Range: -4.7193
Max Act: 4.7193. Min Act: -0.1700
Data Index: 2440119 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7193. Min Range: -4.7193
Max Act: 4.6881. Min Act: -0.1700
Data Index: 249374 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7193. Min Range: -4.7193
Max Act: 4.6568. Min Act: -0.1700
Data Index: 1319636 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7193. Min Range: -4.7193
Max Act: 4.6568. Min Act: -0.1700
Data Index: 4940642 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7193. Min Range: -4.7193
Max Act: 4.6881. Min Act: -0.1700
Data Index: 7392640 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7193. Min Range: -4.7193
Max Act: 4.6256. Min Act: -0.1700
Data Index: 3327270 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7193. Min Range: -4.7193
Max Act: 4.5943. Min Act: -0.1700
Data Index: 4264803 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7193. Min Range: -4.7193
Max Act: 4.6256. Min Act: -0.1700
Data Index: 3127317 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7193. Min Range: -4.7193
Max Act: 4.5943. Min Act: -0.1700
Data Index: 1213058 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7193. Min Range: -4.7193
Max Act: 4.5943. Min Act: -0.1700
Data Index: 869475 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7193. Min Range: -4.7193
Max Act: 4.5943. Min Act: -0.1700
Data Index: 6809217 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7193. Min Range: -4.7193
Max Act: 4.5943. Min Act: -0.1700
Data Index: 1755794 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7193. Min Range: -4.7193
Max Act: 4.5631. Min Act: -0.1700
Data Index: 6130267 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7193. Min Range: -4.7193
Max Act: 4.5631. Min Act: -0.1700
Data Index: 7520915 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7193. Min Range: -4.7193
Max Act: 4.5631. Min Act: -0.1700
Data Index: 120912 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7193. Min Range: -4.7193
Max Act: 4.5318. Min Act: -0.1700
Data Index: 6026638 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7193. Min Range: -4.7193
Max Act: 4.5318. Min Act: -0.1700
Data Index: 6130268 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7193. Min Range: -4.7193
Max Act: 4.5318. Min Act: -0.1700
Data Index: 4230354 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7193. Min Range: -4.7193
Max Act: 4.5318. Min Act: -0.1700
Data Index: 3287674 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7193. Min Range: -4.7193
Max Act: 4.5631. Min Act: -0.1700
Data Index: 6282319 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19