Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1854 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2195. Min Range: -5.2195
Max Act: 5.2195. Min Act: -0.1700
Data Index: 5802512 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2195. Min Range: -5.2195
Max Act: 5.0320. Min Act: -0.1700
Data Index: 5802505 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2195. Min Range: -5.2195
Max Act: 4.9695. Min Act: -0.1700
Data Index: 7987579 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2195. Min Range: -5.2195
Max Act: 4.8133. Min Act: -0.1700
Data Index: 6627683 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2195. Min Range: -5.2195
Max Act: 4.8445. Min Act: -0.1700
Data Index: 5252603 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2195. Min Range: -5.2195
Max Act: 4.7820. Min Act: -0.1700
Data Index: 5686654 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2195. Min Range: -5.2195
Max Act: 4.7820. Min Act: -0.1700
Data Index: 4878500 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2195. Min Range: -5.2195
Max Act: 4.7508. Min Act: -0.1700
Data Index: 2343277 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2195. Min Range: -5.2195
Max Act: 4.7508. Min Act: -0.1700
Data Index: 7623012 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2195. Min Range: -5.2195
Max Act: 4.7195. Min Act: -0.1700
Data Index: 3008222 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2195. Min Range: -5.2195
Max Act: 4.6883. Min Act: -0.1700
Data Index: 7279852 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2195. Min Range: -5.2195
Max Act: 4.6883. Min Act: -0.1700
Data Index: 737433 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2195. Min Range: -5.2195
Max Act: 4.6570. Min Act: -0.1700
Data Index: 6660409 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2195. Min Range: -5.2195
Max Act: 4.6570. Min Act: -0.1700
Data Index: 3747981 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2195. Min Range: -5.2195
Max Act: 4.6570. Min Act: -0.1700
Data Index: 651813 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2195. Min Range: -5.2195
Max Act: 4.6883. Min Act: -0.1700
Data Index: 7623015 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2195. Min Range: -5.2195
Max Act: 4.6570. Min Act: -0.1700
Data Index: 231037 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2195. Min Range: -5.2195
Max Act: 4.6570. Min Act: -0.1700
Data Index: 3601818 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2195. Min Range: -5.2195
Max Act: 4.6570. Min Act: -0.1700
Data Index: 193387 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2195. Min Range: -5.2195
Max Act: 4.6570. Min Act: -0.1700
Data Index: 2735151 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19