Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1406 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.9413. Min Act: -0.1700
Data Index: 7450518 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.8476. Min Act: -0.1700
Data Index: 2034213 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.8163. Min Act: -0.1700
Data Index: 3802794 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7226. Min Act: -0.1700
Data Index: 3287406 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6601. Min Act: -0.1700
Data Index: 8638336 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6288. Min Act: -0.1700
Data Index: 5822426 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6288. Min Act: -0.1700
Data Index: 1841001 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.5976. Min Act: -0.1700
Data Index: 7244917 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6288. Min Act: -0.1700
Data Index: 5415499 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.5976. Min Act: -0.1700
Data Index: 6535377 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.5976. Min Act: -0.1700
Data Index: 8615772 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.5976. Min Act: -0.1700
Data Index: 3287404 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.5351. Min Act: -0.1700
Data Index: 1969469 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.5663. Min Act: -0.1700
Data Index: 6535376 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.5038. Min Act: -0.1700
Data Index: 3462975 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.5351. Min Act: -0.1700
Data Index: 3604536 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.5351. Min Act: -0.1700
Data Index: 4730053 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.5038. Min Act: -0.1700
Data Index: 5778054 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.4726. Min Act: -0.1700
Data Index: 6237771 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.4726. Min Act: -0.1700
Data Index: 3907905 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19