Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 673 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7234. Min Range: -4.7234
Max Act: 4.7234. Min Act: -0.1700
Data Index: 3696068 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7234. Min Range: -4.7234
Max Act: 4.6297. Min Act: -0.1700
Data Index: 3599716 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7234. Min Range: -4.7234
Max Act: 4.5359. Min Act: -0.1700
Data Index: 7910577 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7234. Min Range: -4.7234
Max Act: 4.5047. Min Act: -0.1700
Data Index: 6160709 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7234. Min Range: -4.7234
Max Act: 4.4734. Min Act: -0.1700
Data Index: 2609929 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7234. Min Range: -4.7234
Max Act: 4.4734. Min Act: -0.1700
Data Index: 8217285 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7234. Min Range: -4.7234
Max Act: 4.4734. Min Act: -0.1700
Data Index: 4913123 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7234. Min Range: -4.7234
Max Act: 4.4422. Min Act: -0.1700
Data Index: 7287431 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7234. Min Range: -4.7234
Max Act: 4.4422. Min Act: -0.1700
Data Index: 6965029 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7234. Min Range: -4.7234
Max Act: 4.4109. Min Act: -0.1700
Data Index: 6168291 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7234. Min Range: -4.7234
Max Act: 4.3796. Min Act: -0.1700
Data Index: 3552079 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7234. Min Range: -4.7234
Max Act: 4.3796. Min Act: -0.1700
Data Index: 5986397 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7234. Min Range: -4.7234
Max Act: 4.3484. Min Act: -0.1700
Data Index: 5051188 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7234. Min Range: -4.7234
Max Act: 4.3796. Min Act: -0.1700
Data Index: 5560091 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7234. Min Range: -4.7234
Max Act: 4.3484. Min Act: -0.1700
Data Index: 1221294 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7234. Min Range: -4.7234
Max Act: 4.4109. Min Act: -0.1700
Data Index: 8405658 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7234. Min Range: -4.7234
Max Act: 4.3484. Min Act: -0.1700
Data Index: 6535791 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7234. Min Range: -4.7234
Max Act: 4.3171. Min Act: -0.1700
Data Index: 4186216 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7234. Min Range: -4.7234
Max Act: 4.3484. Min Act: -0.1700
Data Index: 5577714 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7234. Min Range: -4.7234
Max Act: 4.3484. Min Act: -0.1700
Data Index: 6923332 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19