Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1826 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2241. Min Range: -7.2241
Max Act: 7.2241. Min Act: -0.1700
Data Index: 3467730 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2241. Min Range: -7.2241
Max Act: 7.0678. Min Act: -0.1700
Data Index: 7054352 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2241. Min Range: -7.2241
Max Act: 7.0678. Min Act: -0.1700
Data Index: 1427680 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2241. Min Range: -7.2241
Max Act: 7.0053. Min Act: -0.1700
Data Index: 5089205 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2241. Min Range: -7.2241
Max Act: 7.0366. Min Act: -0.1700
Data Index: 5636739 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2241. Min Range: -7.2241
Max Act: 6.9116. Min Act: -0.1700
Data Index: 811408 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2241. Min Range: -7.2241
Max Act: 6.8803. Min Act: -0.1700
Data Index: 1444565 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2241. Min Range: -7.2241
Max Act: 6.8491. Min Act: -0.1700
Data Index: 7561175 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2241. Min Range: -7.2241
Max Act: 6.8491. Min Act: -0.1700
Data Index: 6867046 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2241. Min Range: -7.2241
Max Act: 6.8491. Min Act: -0.1700
Data Index: 3152598 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2241. Min Range: -7.2241
Max Act: 6.8178. Min Act: -0.1700
Data Index: 2104399 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2241. Min Range: -7.2241
Max Act: 6.7866. Min Act: -0.1700
Data Index: 4775825 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2241. Min Range: -7.2241
Max Act: 6.7866. Min Act: -0.1700
Data Index: 6831508 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2241. Min Range: -7.2241
Max Act: 6.7866. Min Act: -0.1700
Data Index: 973292 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2241. Min Range: -7.2241
Max Act: 6.7866. Min Act: -0.1700
Data Index: 511808 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2241. Min Range: -7.2241
Max Act: 6.7553. Min Act: -0.1700
Data Index: 6313077 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2241. Min Range: -7.2241
Max Act: 6.7553. Min Act: -0.1700
Data Index: 1961665 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2241. Min Range: -7.2241
Max Act: 6.7553. Min Act: -0.1700
Data Index: 8560579 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2241. Min Range: -7.2241
Max Act: 6.7241. Min Act: -0.1700
Data Index: 2307916 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2241. Min Range: -7.2241
Max Act: 6.7241. Min Act: -0.1700
Data Index: 3249889 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19