Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4130 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.4708. Min Range: -9.4708
Max Act: 9.4708. Min Act: -0.1700
Data Index: 836525 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4708. Min Range: -9.4708
Max Act: 9.4083. Min Act: -0.1700
Data Index: 8519304 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4708. Min Range: -9.4708
Max Act: 9.2833. Min Act: -0.1700
Data Index: 3983304 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4708. Min Range: -9.4708
Max Act: 9.0958. Min Act: -0.1700
Data Index: 786462 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4708. Min Range: -9.4708
Max Act: 9.0958. Min Act: -0.1700
Data Index: 8271092 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4708. Min Range: -9.4708
Max Act: 9.0333. Min Act: -0.1699
Data Index: 99415 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4708. Min Range: -9.4708
Max Act: 8.9083. Min Act: -0.1700
Data Index: 2427834 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4708. Min Range: -9.4708
Max Act: 8.9083. Min Act: -0.1700
Data Index: 7474236 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4708. Min Range: -9.4708
Max Act: 8.9083. Min Act: -0.1700
Data Index: 6858978 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4708. Min Range: -9.4708
Max Act: 8.8458. Min Act: -0.1700
Data Index: 2904266 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4708. Min Range: -9.4708
Max Act: 8.7833. Min Act: -0.1700
Data Index: 8194151 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4708. Min Range: -9.4708
Max Act: 8.7208. Min Act: -0.1700
Data Index: 394110 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4708. Min Range: -9.4708
Max Act: 8.7833. Min Act: -0.1700
Data Index: 3134416 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4708. Min Range: -9.4708
Max Act: 8.7833. Min Act: -0.1700
Data Index: 1793357 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4708. Min Range: -9.4708
Max Act: 8.7833. Min Act: -0.1700
Data Index: 4688554 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4708. Min Range: -9.4708
Max Act: 8.7833. Min Act: -0.1700
Data Index: 8015955 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4708. Min Range: -9.4708
Max Act: 8.6583. Min Act: -0.1700
Data Index: 165610 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4708. Min Range: -9.4708
Max Act: 8.6583. Min Act: -0.1700
Data Index: 5130046 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4708. Min Range: -9.4708
Max Act: 8.5958. Min Act: -0.1700
Data Index: 488106 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4708. Min Range: -9.4708
Max Act: 8.5958. Min Act: -0.1700
Data Index: 8327228 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19