Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3771 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.3325. Min Range: -10.3325
Max Act: 10.3325. Min Act: -0.1700
Data Index: 7114893 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3325. Min Range: -10.3325
Max Act: 9.9575. Min Act: -0.1700
Data Index: 8531569 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3325. Min Range: -10.3325
Max Act: 9.7700. Min Act: -0.1700
Data Index: 7064087 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3325. Min Range: -10.3325
Max Act: 9.7075. Min Act: -0.1700
Data Index: 3305852 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3325. Min Range: -10.3325
Max Act: 9.7075. Min Act: -0.1700
Data Index: 2168691 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3325. Min Range: -10.3325
Max Act: 9.4575. Min Act: -0.1700
Data Index: 6936079 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3325. Min Range: -10.3325
Max Act: 9.3950. Min Act: -0.1700
Data Index: 3219329 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3325. Min Range: -10.3325
Max Act: 9.3325. Min Act: -0.1700
Data Index: 7620041 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3325. Min Range: -10.3325
Max Act: 9.3325. Min Act: -0.1700
Data Index: 4243022 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3325. Min Range: -10.3325
Max Act: 9.3325. Min Act: -0.1700
Data Index: 4226846 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3325. Min Range: -10.3325
Max Act: 9.3325. Min Act: -0.1700
Data Index: 7758638 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3325. Min Range: -10.3325
Max Act: 9.2700. Min Act: -0.1700
Data Index: 7932552 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3325. Min Range: -10.3325
Max Act: 9.2700. Min Act: -0.1700
Data Index: 7098486 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3325. Min Range: -10.3325
Max Act: 9.2700. Min Act: -0.1700
Data Index: 863157 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3325. Min Range: -10.3325
Max Act: 9.2700. Min Act: -0.1700
Data Index: 7121176 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3325. Min Range: -10.3325
Max Act: 9.2700. Min Act: -0.1700
Data Index: 959366 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3325. Min Range: -10.3325
Max Act: 9.2075. Min Act: -0.1700
Data Index: 5700868 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3325. Min Range: -10.3325
Max Act: 9.2075. Min Act: -0.1700
Data Index: 6942128 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3325. Min Range: -10.3325
Max Act: 9.1450. Min Act: -0.1700
Data Index: 3303305 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3325. Min Range: -10.3325
Max Act: 9.1450. Min Act: -0.1700
Data Index: 6262980 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19