Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 309 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7179. Min Range: -3.7179
Max Act: 3.7179. Min Act: -0.1700
Data Index: 4295270 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7179. Min Range: -3.7179
Max Act: 3.6397. Min Act: -0.1700
Data Index: 2659076 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7179. Min Range: -3.7179
Max Act: 3.4988. Min Act: -0.1700
Data Index: 8141125 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7179. Min Range: -3.7179
Max Act: 3.4988. Min Act: -0.1700
Data Index: 2221157 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7179. Min Range: -3.7179
Max Act: 3.4518. Min Act: -0.1700
Data Index: 5426659 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7179. Min Range: -3.7179
Max Act: 3.4518. Min Act: -0.1700
Data Index: 2983809 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7179. Min Range: -3.7179
Max Act: 3.4362. Min Act: -0.1700
Data Index: 5271815 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7179. Min Range: -3.7179
Max Act: 3.4518. Min Act: -0.1700
Data Index: 5889428 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7179. Min Range: -3.7179
Max Act: 3.4048. Min Act: -0.1700
Data Index: 8790940 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7179. Min Range: -3.7179
Max Act: 3.3734. Min Act: -0.1700
Data Index: 7845941 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7179. Min Range: -3.7179
Max Act: 3.4205. Min Act: -0.1700
Data Index: 599440 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7179. Min Range: -3.7179
Max Act: 3.3578. Min Act: -0.1700
Data Index: 3602967 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7179. Min Range: -3.7179
Max Act: 3.3891. Min Act: -0.1700
Data Index: 1479914 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7179. Min Range: -3.7179
Max Act: 3.3578. Min Act: -0.1700
Data Index: 8661695 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7179. Min Range: -3.7179
Max Act: 3.3578. Min Act: -0.1700
Data Index: 4572011 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7179. Min Range: -3.7179
Max Act: 3.3421. Min Act: -0.1700
Data Index: 8580162 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7179. Min Range: -3.7179
Max Act: 3.3734. Min Act: -0.1700
Data Index: 3412633 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7179. Min Range: -3.7179
Max Act: 3.3578. Min Act: -0.1700
Data Index: 6210816 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7179. Min Range: -3.7179
Max Act: 3.3421. Min Act: -0.1700
Data Index: 7815156 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7179. Min Range: -3.7179
Max Act: 3.3107. Min Act: -0.1700
Data Index: 3901336 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19