Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2371 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2226. Min Range: -6.2226
Max Act: 6.2226. Min Act: -0.1700
Data Index: 6096061 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2226. Min Range: -6.2226
Max Act: 6.0976. Min Act: -0.1700
Data Index: 2869692 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2226. Min Range: -6.2226
Max Act: 5.9726. Min Act: -0.1700
Data Index: 5937465 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2226. Min Range: -6.2226
Max Act: 5.9726. Min Act: -0.1700
Data Index: 5319240 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2226. Min Range: -6.2226
Max Act: 5.9101. Min Act: -0.1700
Data Index: 5876247 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2226. Min Range: -6.2226
Max Act: 5.7851. Min Act: -0.1700
Data Index: 5911067 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2226. Min Range: -6.2226
Max Act: 5.6913. Min Act: -0.1700
Data Index: 970181 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2226. Min Range: -6.2226
Max Act: 5.7538. Min Act: -0.1700
Data Index: 1977196 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2226. Min Range: -6.2226
Max Act: 5.6913. Min Act: -0.1700
Data Index: 4211048 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2226. Min Range: -6.2226
Max Act: 5.6913. Min Act: -0.1700
Data Index: 436313 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2226. Min Range: -6.2226
Max Act: 5.7226. Min Act: -0.1700
Data Index: 2040828 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2226. Min Range: -6.2226
Max Act: 5.6913. Min Act: -0.1700
Data Index: 1950889 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2226. Min Range: -6.2226
Max Act: 5.6601. Min Act: -0.1700
Data Index: 8506383 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2226. Min Range: -6.2226
Max Act: 5.6288. Min Act: -0.1700
Data Index: 1216964 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2226. Min Range: -6.2226
Max Act: 5.6288. Min Act: -0.1700
Data Index: 3627339 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2226. Min Range: -6.2226
Max Act: 5.6288. Min Act: -0.1700
Data Index: 6372076 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2226. Min Range: -6.2226
Max Act: 5.5976. Min Act: -0.1700
Data Index: 1670069 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2226. Min Range: -6.2226
Max Act: 5.5976. Min Act: -0.1700
Data Index: 3659167 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2226. Min Range: -6.2226
Max Act: 5.5663. Min Act: -0.1700
Data Index: 2258784 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2226. Min Range: -6.2226
Max Act: 5.5038. Min Act: -0.1700
Data Index: 6862263 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19