Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3269 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.0163. Min Range: -15.0163
Max Act: 15.0163. Min Act: -0.1700
Data Index: 6496360 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.0163. Min Range: -15.0163
Max Act: 14.7663. Min Act: -0.1700
Data Index: 4284499 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.0163. Min Range: -15.0163
Max Act: 14.7663. Min Act: -0.1700
Data Index: 5117037 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.0163. Min Range: -15.0163
Max Act: 14.7038. Min Act: -0.1700
Data Index: 1537663 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.0163. Min Range: -15.0163
Max Act: 14.4538. Min Act: -0.1700
Data Index: 5874065 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.0163. Min Range: -15.0163
Max Act: 14.3913. Min Act: -0.1700
Data Index: 1959964 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.0163. Min Range: -15.0163
Max Act: 14.3913. Min Act: -0.1700
Data Index: 5059151 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.0163. Min Range: -15.0163
Max Act: 14.3913. Min Act: -0.1700
Data Index: 1676761 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.0163. Min Range: -15.0163
Max Act: 14.3288. Min Act: -0.1700
Data Index: 1600426 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.0163. Min Range: -15.0163
Max Act: 14.2663. Min Act: -0.1700
Data Index: 4641766 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.0163. Min Range: -15.0163
Max Act: 14.2663. Min Act: -0.1700
Data Index: 1776541 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.0163. Min Range: -15.0163
Max Act: 14.2038. Min Act: -0.1700
Data Index: 3615947 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.0163. Min Range: -15.0163
Max Act: 14.2663. Min Act: -0.1700
Data Index: 1702587 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.0163. Min Range: -15.0163
Max Act: 14.1413. Min Act: -0.1700
Data Index: 5537166 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.0163. Min Range: -15.0163
Max Act: 14.2038. Min Act: -0.1700
Data Index: 684348 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.0163. Min Range: -15.0163
Max Act: 14.0788. Min Act: -0.1700
Data Index: 584651 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.0163. Min Range: -15.0163
Max Act: 14.0788. Min Act: -0.1700
Data Index: 925645 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.0163. Min Range: -15.0163
Max Act: 14.0163. Min Act: -0.1700
Data Index: 5239053 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.0163. Min Range: -15.0163
Max Act: 14.0163. Min Act: -0.1700
Data Index: 5021440 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.0163. Min Range: -15.0163
Max Act: 13.9538. Min Act: -0.1700
Data Index: 2582300 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19