Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2592 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.4942. Min Act: -0.1700
Data Index: 6218450 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.4630. Min Act: -0.1700
Data Index: 3087526 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.3692. Min Act: -0.1700
Data Index: 6258347 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.3380. Min Act: -0.1700
Data Index: 8230148 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.3067. Min Act: -0.1700
Data Index: 3420382 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.3067. Min Act: -0.1700
Data Index: 8592074 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.2130. Min Act: -0.1700
Data Index: 7858292 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.1817. Min Act: -0.1700
Data Index: 2824320 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.2130. Min Act: -0.1700
Data Index: 5851526 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.1817. Min Act: -0.1700
Data Index: 272483 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.1817. Min Act: -0.1700
Data Index: 5343624 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.1817. Min Act: -0.1700
Data Index: 152078 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.1192. Min Act: -0.1700
Data Index: 372863 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.1192. Min Act: -0.1700
Data Index: 170486 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.1505. Min Act: -0.1700
Data Index: 7425244 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.1505. Min Act: -0.1700
Data Index: 182426 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.1505. Min Act: -0.1700
Data Index: 115893 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.1192. Min Act: -0.1700
Data Index: 2866799 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.1192. Min Act: -0.1700
Data Index: 8109493 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4942. Min Range: -5.4942
Max Act: 5.1192. Min Act: -0.1700
Data Index: 3056243 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19