Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1890 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3608. Min Range: -5.3608
Max Act: 5.3608. Min Act: -0.1700
Data Index: 3427418 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3608. Min Range: -5.3608
Max Act: 5.3608. Min Act: -0.1700
Data Index: 5202196 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3608. Min Range: -5.3608
Max Act: 5.2358. Min Act: -0.1700
Data Index: 5992769 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3608. Min Range: -5.3608
Max Act: 5.2045. Min Act: -0.1700
Data Index: 8091403 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3608. Min Range: -5.3608
Max Act: 5.1108. Min Act: -0.1700
Data Index: 5812893 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3608. Min Range: -5.3608
Max Act: 5.0795. Min Act: -0.1700
Data Index: 546262 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3608. Min Range: -5.3608
Max Act: 5.0483. Min Act: -0.1700
Data Index: 5848534 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3608. Min Range: -5.3608
Max Act: 5.0795. Min Act: -0.1700
Data Index: 3383854 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3608. Min Range: -5.3608
Max Act: 5.0795. Min Act: -0.1700
Data Index: 3427419 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3608. Min Range: -5.3608
Max Act: 5.0170. Min Act: -0.1700
Data Index: 2113153 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3608. Min Range: -5.3608
Max Act: 5.0170. Min Act: -0.1700
Data Index: 8731478 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3608. Min Range: -5.3608
Max Act: 4.9858. Min Act: -0.1700
Data Index: 6240056 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3608. Min Range: -5.3608
Max Act: 4.9858. Min Act: -0.1700
Data Index: 7833549 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3608. Min Range: -5.3608
Max Act: 4.9858. Min Act: -0.1700
Data Index: 3925963 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3608. Min Range: -5.3608
Max Act: 4.9233. Min Act: -0.1700
Data Index: 5306322 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3608. Min Range: -5.3608
Max Act: 4.9545. Min Act: -0.1700
Data Index: 6216256 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3608. Min Range: -5.3608
Max Act: 4.9545. Min Act: -0.1700
Data Index: 966780 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3608. Min Range: -5.3608
Max Act: 4.9233. Min Act: -0.1700
Data Index: 7825239 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3608. Min Range: -5.3608
Max Act: 4.9233. Min Act: -0.1700
Data Index: 1353278 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3608. Min Range: -5.3608
Max Act: 4.8920. Min Act: -0.1700
Data Index: 4722981 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19