Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 855 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.3715. Min Act: -0.1700
Data Index: 416020 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.3224. Min Act: -0.1700
Data Index: 5901120 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.3552. Min Act: -0.1700
Data Index: 4631381 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.3552. Min Act: -0.1700
Data Index: 8796679 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.3388. Min Act: -0.1700
Data Index: 8084507 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.3224. Min Act: -0.1700
Data Index: 2989051 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.3388. Min Act: -0.1700
Data Index: 8689173 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.3224. Min Act: -0.1700
Data Index: 5448459 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.3059. Min Act: -0.1700
Data Index: 6656449 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2895. Min Act: -0.1700
Data Index: 6069886 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2565. Min Act: -0.1700
Data Index: 6804206 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2730. Min Act: -0.1700
Data Index: 4404082 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2730. Min Act: -0.1700
Data Index: 3824301 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2565. Min Act: -0.1700
Data Index: 3904512 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2730. Min Act: -0.1700
Data Index: 5558406 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2565. Min Act: -0.1700
Data Index: 6257257 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2400. Min Act: -0.1700
Data Index: 5169492 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2234. Min Act: -0.1700
Data Index: 1021775 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2400. Min Act: -0.1700
Data Index: 2905959 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2234. Min Act: -0.1700
Data Index: 5029853 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19