Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 616 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3179. Min Range: -9.3179
Max Act: 9.3179. Min Act: -0.1700
Data Index: 8608210 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3179. Min Range: -9.3179
Max Act: 9.0054. Min Act: -0.1700
Data Index: 5200317 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3179. Min Range: -9.3179
Max Act: 8.9429. Min Act: -0.1700
Data Index: 4289153 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3179. Min Range: -9.3179
Max Act: 8.8804. Min Act: -0.1700
Data Index: 1450887 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3179. Min Range: -9.3179
Max Act: 8.8179. Min Act: -0.1700
Data Index: 4289154 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3179. Min Range: -9.3179
Max Act: 8.7554. Min Act: -0.1700
Data Index: 6351136 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3179. Min Range: -9.3179
Max Act: 8.6929. Min Act: -0.1700
Data Index: 638848 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3179. Min Range: -9.3179
Max Act: 8.6929. Min Act: -0.1700
Data Index: 2817646 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3179. Min Range: -9.3179
Max Act: 8.6929. Min Act: -0.1700
Data Index: 7876964 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3179. Min Range: -9.3179
Max Act: 8.6304. Min Act: -0.1700
Data Index: 7695103 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3179. Min Range: -9.3179
Max Act: 8.6304. Min Act: -0.1700
Data Index: 6815329 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3179. Min Range: -9.3179
Max Act: 8.6304. Min Act: -0.1700
Data Index: 3834836 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3179. Min Range: -9.3179
Max Act: 8.5679. Min Act: -0.1700
Data Index: 2920881 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3179. Min Range: -9.3179
Max Act: 8.5054. Min Act: -0.1700
Data Index: 1390278 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3179. Min Range: -9.3179
Max Act: 8.5054. Min Act: -0.1700
Data Index: 5608417 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3179. Min Range: -9.3179
Max Act: 8.4429. Min Act: -0.1700
Data Index: 3132404 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3179. Min Range: -9.3179
Max Act: 8.4429. Min Act: -0.1700
Data Index: 28396 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3179. Min Range: -9.3179
Max Act: 8.4429. Min Act: -0.1700
Data Index: 2852992 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3179. Min Range: -9.3179
Max Act: 8.4429. Min Act: -0.1700
Data Index: 5398129 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3179. Min Range: -9.3179
Max Act: 8.3804. Min Act: -0.1700
Data Index: 3201042 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19