Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3246 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4397. Min Range: -9.4397
Max Act: 9.4397. Min Act: -0.1700
Data Index: 6910960 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4397. Min Range: -9.4397
Max Act: 9.3772. Min Act: -0.1700
Data Index: 6020505 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4397. Min Range: -9.4397
Max Act: 9.3147. Min Act: -0.1700
Data Index: 4445781 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4397. Min Range: -9.4397
Max Act: 9.3147. Min Act: -0.1700
Data Index: 522093 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4397. Min Range: -9.4397
Max Act: 9.1272. Min Act: -0.1700
Data Index: 6012950 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4397. Min Range: -9.4397
Max Act: 9.1272. Min Act: -0.1700
Data Index: 8282749 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4397. Min Range: -9.4397
Max Act: 9.0022. Min Act: -0.1700
Data Index: 3819423 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4397. Min Range: -9.4397
Max Act: 9.1272. Min Act: -0.1700
Data Index: 5360721 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4397. Min Range: -9.4397
Max Act: 9.0647. Min Act: -0.1700
Data Index: 7655938 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4397. Min Range: -9.4397
Max Act: 8.8772. Min Act: -0.1700
Data Index: 1870481 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4397. Min Range: -9.4397
Max Act: 8.9397. Min Act: -0.1700
Data Index: 7418080 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4397. Min Range: -9.4397
Max Act: 8.9397. Min Act: -0.1700
Data Index: 1482555 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4397. Min Range: -9.4397
Max Act: 8.9397. Min Act: -0.1700
Data Index: 7698956 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4397. Min Range: -9.4397
Max Act: 8.9397. Min Act: -0.1700
Data Index: 4922313 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4397. Min Range: -9.4397
Max Act: 9.0022. Min Act: -0.1700
Data Index: 2666746 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4397. Min Range: -9.4397
Max Act: 8.8772. Min Act: -0.1700
Data Index: 5735920 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4397. Min Range: -9.4397
Max Act: 8.8772. Min Act: -0.1700
Data Index: 16792 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4397. Min Range: -9.4397
Max Act: 8.8772. Min Act: -0.1700
Data Index: 6366537 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4397. Min Range: -9.4397
Max Act: 8.8147. Min Act: -0.1700
Data Index: 378937 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4397. Min Range: -9.4397
Max Act: 8.8772. Min Act: -0.1700
Data Index: 2949353 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19