Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4712 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5351. Min Range: -7.5351
Max Act: 7.5351. Min Act: -0.1700
Data Index: 5426778 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5351. Min Range: -7.5351
Max Act: 6.8476. Min Act: -0.1700
Data Index: 4144515 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5351. Min Range: -7.5351
Max Act: 6.8476. Min Act: -0.1700
Data Index: 7846820 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5351. Min Range: -7.5351
Max Act: 6.7851. Min Act: -0.1700
Data Index: 4216946 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5351. Min Range: -7.5351
Max Act: 6.6913. Min Act: -0.1700
Data Index: 3563476 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5351. Min Range: -7.5351
Max Act: 6.6288. Min Act: -0.1700
Data Index: 7846811 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5351. Min Range: -7.5351
Max Act: 6.5663. Min Act: -0.1700
Data Index: 1647024 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5351. Min Range: -7.5351
Max Act: 6.5351. Min Act: -0.1700
Data Index: 7198898 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5351. Min Range: -7.5351
Max Act: 6.5038. Min Act: -0.1700
Data Index: 5290043 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5351. Min Range: -7.5351
Max Act: 6.4726. Min Act: -0.1700
Data Index: 5290047 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5351. Min Range: -7.5351
Max Act: 6.5038. Min Act: -0.1700
Data Index: 1225453 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5351. Min Range: -7.5351
Max Act: 6.3788. Min Act: -0.1700
Data Index: 4996966 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5351. Min Range: -7.5351
Max Act: 6.3788. Min Act: -0.1700
Data Index: 7846796 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5351. Min Range: -7.5351
Max Act: 6.3476. Min Act: -0.1700
Data Index: 5980383 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5351. Min Range: -7.5351
Max Act: 6.3476. Min Act: -0.1700
Data Index: 8208750 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5351. Min Range: -7.5351
Max Act: 6.3476. Min Act: -0.1700
Data Index: 8560430 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5351. Min Range: -7.5351
Max Act: 6.3163. Min Act: -0.1700
Data Index: 7198891 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5351. Min Range: -7.5351
Max Act: 6.3476. Min Act: -0.1700
Data Index: 8365358 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5351. Min Range: -7.5351
Max Act: 6.3163. Min Act: -0.1700
Data Index: 5639426 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5351. Min Range: -7.5351
Max Act: 6.3163. Min Act: -0.1700
Data Index: 2017613 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19