Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 921 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4572. Min Range: -7.4572
Max Act: 7.4572. Min Act: -0.1700
Data Index: 6298135 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4572. Min Range: -7.4572
Max Act: 7.3009. Min Act: -0.1700
Data Index: 8789264 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4572. Min Range: -7.4572
Max Act: 7.2072. Min Act: -0.1700
Data Index: 4797281 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4572. Min Range: -7.4572
Max Act: 7.1447. Min Act: -0.1700
Data Index: 4931368 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4572. Min Range: -7.4572
Max Act: 7.1134. Min Act: -0.1700
Data Index: 5786726 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4572. Min Range: -7.4572
Max Act: 7.0509. Min Act: -0.1700
Data Index: 7858765 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4572. Min Range: -7.4572
Max Act: 6.9259. Min Act: -0.1700
Data Index: 894613 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4572. Min Range: -7.4572
Max Act: 6.8634. Min Act: -0.1700
Data Index: 349007 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4572. Min Range: -7.4572
Max Act: 6.8322. Min Act: -0.1700
Data Index: 615427 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4572. Min Range: -7.4572
Max Act: 6.7072. Min Act: -0.1700
Data Index: 491130 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4572. Min Range: -7.4572
Max Act: 6.6447. Min Act: -0.1700
Data Index: 8313717 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4572. Min Range: -7.4572
Max Act: 6.6134. Min Act: -0.1700
Data Index: 3381742 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4572. Min Range: -7.4572
Max Act: 6.6134. Min Act: -0.1700
Data Index: 3182121 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4572. Min Range: -7.4572
Max Act: 6.6134. Min Act: -0.1700
Data Index: 326033 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4572. Min Range: -7.4572
Max Act: 6.5197. Min Act: -0.1700
Data Index: 7812747 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4572. Min Range: -7.4572
Max Act: 6.5822. Min Act: -0.1700
Data Index: 8747481 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4572. Min Range: -7.4572
Max Act: 6.5822. Min Act: -0.1700
Data Index: 8405284 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4572. Min Range: -7.4572
Max Act: 6.5509. Min Act: -0.1700
Data Index: 6708184 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4572. Min Range: -7.4572
Max Act: 6.5197. Min Act: -0.1700
Data Index: 5409254 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4572. Min Range: -7.4572
Max Act: 6.4884. Min Act: -0.1700
Data Index: 7510503 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19