Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3716 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2538. Min Range: -7.2538
Max Act: 7.2538. Min Act: -0.1700
Data Index: 7259135 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2538. Min Range: -7.2538
Max Act: 7.1913. Min Act: -0.1700
Data Index: 3812048 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2538. Min Range: -7.2538
Max Act: 7.1601. Min Act: -0.1700
Data Index: 578285 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2538. Min Range: -7.2538
Max Act: 7.0351. Min Act: -0.1700
Data Index: 4842201 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2538. Min Range: -7.2538
Max Act: 6.9726. Min Act: -0.1700
Data Index: 8143030 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2538. Min Range: -7.2538
Max Act: 6.8788. Min Act: -0.1700
Data Index: 7383196 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2538. Min Range: -7.2538
Max Act: 6.8476. Min Act: -0.1700
Data Index: 1950550 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2538. Min Range: -7.2538
Max Act: 6.8476. Min Act: -0.1700
Data Index: 420622 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2538. Min Range: -7.2538
Max Act: 6.8476. Min Act: -0.1700
Data Index: 1500103 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2538. Min Range: -7.2538
Max Act: 6.8163. Min Act: -0.1700
Data Index: 1161876 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2538. Min Range: -7.2538
Max Act: 6.7538. Min Act: -0.1700
Data Index: 7324602 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2538. Min Range: -7.2538
Max Act: 6.7538. Min Act: -0.1700
Data Index: 3565659 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2538. Min Range: -7.2538
Max Act: 6.6913. Min Act: -0.1700
Data Index: 8294085 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2538. Min Range: -7.2538
Max Act: 6.7226. Min Act: -0.1700
Data Index: 4216950 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2538. Min Range: -7.2538
Max Act: 6.6913. Min Act: -0.1700
Data Index: 7344263 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2538. Min Range: -7.2538
Max Act: 6.6913. Min Act: -0.1700
Data Index: 4381915 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2538. Min Range: -7.2538
Max Act: 6.6288. Min Act: -0.1700
Data Index: 6347096 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2538. Min Range: -7.2538
Max Act: 6.5976. Min Act: -0.1700
Data Index: 5741780 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2538. Min Range: -7.2538
Max Act: 6.6288. Min Act: -0.1700
Data Index: 6828067 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2538. Min Range: -7.2538
Max Act: 6.6288. Min Act: -0.1700
Data Index: 1367282 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19