Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2172 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5092. Min Range: -5.5092
Max Act: 5.5092. Min Act: -0.1700
Data Index: 2848898 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5092. Min Range: -5.5092
Max Act: 5.4467. Min Act: -0.1700
Data Index: 8137969 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5092. Min Range: -5.5092
Max Act: 5.4154. Min Act: -0.1700
Data Index: 1527035 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5092. Min Range: -5.5092
Max Act: 5.3842. Min Act: -0.1700
Data Index: 8035989 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5092. Min Range: -5.5092
Max Act: 5.3217. Min Act: -0.1700
Data Index: 4021665 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5092. Min Range: -5.5092
Max Act: 5.3217. Min Act: -0.1700
Data Index: 214962 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5092. Min Range: -5.5092
Max Act: 5.3217. Min Act: -0.1700
Data Index: 1171046 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5092. Min Range: -5.5092
Max Act: 5.3529. Min Act: -0.1700
Data Index: 342384 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5092. Min Range: -5.5092
Max Act: 5.3217. Min Act: -0.1700
Data Index: 74904 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5092. Min Range: -5.5092
Max Act: 5.3529. Min Act: -0.1700
Data Index: 4160796 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5092. Min Range: -5.5092
Max Act: 5.3217. Min Act: -0.1700
Data Index: 1326161 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5092. Min Range: -5.5092
Max Act: 5.2904. Min Act: -0.1700
Data Index: 8188575 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5092. Min Range: -5.5092
Max Act: 5.3217. Min Act: -0.1700
Data Index: 8018066 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5092. Min Range: -5.5092
Max Act: 5.2904. Min Act: -0.1700
Data Index: 4151245 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5092. Min Range: -5.5092
Max Act: 5.2904. Min Act: -0.1700
Data Index: 4449106 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5092. Min Range: -5.5092
Max Act: 5.2592. Min Act: -0.1700
Data Index: 1554407 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5092. Min Range: -5.5092
Max Act: 5.2592. Min Act: -0.1700
Data Index: 2145523 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5092. Min Range: -5.5092
Max Act: 5.2592. Min Act: -0.1700
Data Index: 2272867 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5092. Min Range: -5.5092
Max Act: 5.2279. Min Act: -0.1700
Data Index: 2248083 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5092. Min Range: -5.5092
Max Act: 5.2279. Min Act: -0.1700
Data Index: 2550243 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19