Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3197 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0882. Min Range: -5.0882
Max Act: 5.0882. Min Act: -0.1700
Data Index: 1301466 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0882. Min Range: -5.0882
Max Act: 5.0257. Min Act: -0.1700
Data Index: 1470821 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0882. Min Range: -5.0882
Max Act: 4.9319. Min Act: -0.1700
Data Index: 6518803 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0882. Min Range: -5.0882
Max Act: 4.9319. Min Act: -0.1700
Data Index: 6352191 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0882. Min Range: -5.0882
Max Act: 4.8694. Min Act: -0.1700
Data Index: 1552319 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0882. Min Range: -5.0882
Max Act: 4.8694. Min Act: -0.1700
Data Index: 1965283 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0882. Min Range: -5.0882
Max Act: 4.8694. Min Act: -0.1700
Data Index: 2786951 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0882. Min Range: -5.0882
Max Act: 4.8382. Min Act: -0.1700
Data Index: 7948020 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0882. Min Range: -5.0882
Max Act: 4.8694. Min Act: -0.1700
Data Index: 1503411 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0882. Min Range: -5.0882
Max Act: 4.8382. Min Act: -0.1700
Data Index: 473280 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0882. Min Range: -5.0882
Max Act: 4.7757. Min Act: -0.1700
Data Index: 1152054 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0882. Min Range: -5.0882
Max Act: 4.7757. Min Act: -0.1700
Data Index: 7594217 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0882. Min Range: -5.0882
Max Act: 4.7132. Min Act: -0.1700
Data Index: 415345 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0882. Min Range: -5.0882
Max Act: 4.6819. Min Act: -0.1700
Data Index: 2744703 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0882. Min Range: -5.0882
Max Act: 4.6819. Min Act: -0.1700
Data Index: 2491108 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0882. Min Range: -5.0882
Max Act: 4.6507. Min Act: -0.1700
Data Index: 6464553 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0882. Min Range: -5.0882
Max Act: 4.6507. Min Act: -0.1700
Data Index: 3718512 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0882. Min Range: -5.0882
Max Act: 4.6507. Min Act: -0.1700
Data Index: 118711 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0882. Min Range: -5.0882
Max Act: 4.6819. Min Act: -0.1700
Data Index: 6349970 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0882. Min Range: -5.0882
Max Act: 4.6507. Min Act: -0.1700
Data Index: 5538084 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19