Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3826 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.4805. Min Act: -0.1700
Data Index: 2898226 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.3867. Min Act: -0.1700
Data Index: 7049196 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.3555. Min Act: -0.1700
Data Index: 8803858 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.3242. Min Act: -0.1700
Data Index: 3576154 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2930. Min Act: -0.1700
Data Index: 7465742 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2930. Min Act: -0.1700
Data Index: 8381015 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2617. Min Act: -0.1700
Data Index: 157471 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2305. Min Act: -0.1700
Data Index: 6601562 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1992. Min Act: -0.1700
Data Index: 3339620 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1992. Min Act: -0.1700
Data Index: 5505149 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1992. Min Act: -0.1700
Data Index: 7821100 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1680. Min Act: -0.1700
Data Index: 7603035 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1680. Min Act: -0.1700
Data Index: 4826930 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1367. Min Act: -0.1700
Data Index: 8428613 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1367. Min Act: -0.1700
Data Index: 680254 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1680. Min Act: -0.1700
Data Index: 4550470 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1367. Min Act: -0.1700
Data Index: 8642559 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1055. Min Act: -0.1700
Data Index: 4188287 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1055. Min Act: -0.1700
Data Index: 6896407 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1367. Min Act: -0.1700
Data Index: 8202350 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19