Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2852 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8273. Min Range: -5.8273
Max Act: 5.8273. Min Act: -0.1700
Data Index: 8567672 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8273. Min Range: -5.8273
Max Act: 5.6398. Min Act: -0.1700
Data Index: 5261565 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8273. Min Range: -5.8273
Max Act: 5.5773. Min Act: -0.1700
Data Index: 4652474 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8273. Min Range: -5.8273
Max Act: 5.5148. Min Act: -0.1700
Data Index: 8550528 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8273. Min Range: -5.8273
Max Act: 5.4835. Min Act: -0.1700
Data Index: 5498464 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8273. Min Range: -5.8273
Max Act: 5.4835. Min Act: -0.1700
Data Index: 7007149 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8273. Min Range: -5.8273
Max Act: 5.5148. Min Act: -0.1700
Data Index: 5505403 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8273. Min Range: -5.8273
Max Act: 5.4523. Min Act: -0.1700
Data Index: 2347489 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8273. Min Range: -5.8273
Max Act: 5.4523. Min Act: -0.1700
Data Index: 532853 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8273. Min Range: -5.8273
Max Act: 5.4523. Min Act: -0.1700
Data Index: 7600516 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8273. Min Range: -5.8273
Max Act: 5.3898. Min Act: -0.1700
Data Index: 6703165 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8273. Min Range: -5.8273
Max Act: 5.3898. Min Act: -0.1700
Data Index: 1955503 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8273. Min Range: -5.8273
Max Act: 5.3898. Min Act: -0.1700
Data Index: 8383958 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8273. Min Range: -5.8273
Max Act: 5.3898. Min Act: -0.1700
Data Index: 6931602 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8273. Min Range: -5.8273
Max Act: 5.3585. Min Act: -0.1700
Data Index: 519266 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8273. Min Range: -5.8273
Max Act: 5.3273. Min Act: -0.1700
Data Index: 1591187 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8273. Min Range: -5.8273
Max Act: 5.3585. Min Act: -0.1700
Data Index: 2808060 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8273. Min Range: -5.8273
Max Act: 5.3585. Min Act: -0.1700
Data Index: 7773382 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8273. Min Range: -5.8273
Max Act: 5.3273. Min Act: -0.1700
Data Index: 4718860 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8273. Min Range: -5.8273
Max Act: 5.2960. Min Act: -0.1700
Data Index: 6996525 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19