Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 300 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5187. Min Range: -3.5187
Max Act: 3.5187. Min Act: -0.1700
Data Index: 3940514 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5187. Min Range: -3.5187
Max Act: 3.4247. Min Act: -0.1700
Data Index: 6910856 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5187. Min Range: -3.5187
Max Act: 3.4090. Min Act: -0.1700
Data Index: 2984838 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5187. Min Range: -3.5187
Max Act: 3.3620. Min Act: -0.1700
Data Index: 1790625 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5187. Min Range: -3.5187
Max Act: 3.3620. Min Act: -0.1700
Data Index: 4208105 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5187. Min Range: -3.5187
Max Act: 3.3463. Min Act: -0.1700
Data Index: 8502696 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5187. Min Range: -3.5187
Max Act: 3.3306. Min Act: -0.1700
Data Index: 853930 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5187. Min Range: -3.5187
Max Act: 3.3306. Min Act: -0.1700
Data Index: 5545510 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5187. Min Range: -3.5187
Max Act: 3.3306. Min Act: -0.1700
Data Index: 3890141 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5187. Min Range: -3.5187
Max Act: 3.3306. Min Act: -0.1700
Data Index: 6670012 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5187. Min Range: -3.5187
Max Act: 3.3306. Min Act: -0.1700
Data Index: 2505186 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5187. Min Range: -3.5187
Max Act: 3.3306. Min Act: -0.1700
Data Index: 8015104 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5187. Min Range: -3.5187
Max Act: 3.3149. Min Act: -0.1700
Data Index: 608236 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5187. Min Range: -3.5187
Max Act: 3.2992. Min Act: -0.1700
Data Index: 1538304 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5187. Min Range: -3.5187
Max Act: 3.2678. Min Act: -0.1700
Data Index: 872388 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5187. Min Range: -3.5187
Max Act: 3.2678. Min Act: -0.1700
Data Index: 2781588 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5187. Min Range: -3.5187
Max Act: 3.2678. Min Act: -0.1700
Data Index: 2868421 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5187. Min Range: -3.5187
Max Act: 3.2678. Min Act: -0.1700
Data Index: 6893593 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5187. Min Range: -3.5187
Max Act: 3.2521. Min Act: -0.1700
Data Index: 1602543 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5187. Min Range: -3.5187
Max Act: 3.2364. Min Act: -0.1700
Data Index: 7917996 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19