Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1563 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3175. Min Range: -7.3175
Max Act: 7.3175. Min Act: -0.1700
Data Index: 6688111 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3175. Min Range: -7.3175
Max Act: 7.2862. Min Act: -0.1700
Data Index: 3777744 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3175. Min Range: -7.3175
Max Act: 7.2237. Min Act: -0.1700
Data Index: 8760786 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3175. Min Range: -7.3175
Max Act: 7.1300. Min Act: -0.1700
Data Index: 5493600 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3175. Min Range: -7.3175
Max Act: 7.0050. Min Act: -0.1700
Data Index: 4861119 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3175. Min Range: -7.3175
Max Act: 6.9737. Min Act: -0.1700
Data Index: 2504806 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3175. Min Range: -7.3175
Max Act: 6.8800. Min Act: -0.1700
Data Index: 2132028 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3175. Min Range: -7.3175
Max Act: 6.8487. Min Act: -0.1700
Data Index: 5976517 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3175. Min Range: -7.3175
Max Act: 6.9112. Min Act: -0.1700
Data Index: 7453168 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3175. Min Range: -7.3175
Max Act: 6.8800. Min Act: -0.1700
Data Index: 5050990 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3175. Min Range: -7.3175
Max Act: 6.8800. Min Act: -0.1700
Data Index: 27068 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3175. Min Range: -7.3175
Max Act: 6.8800. Min Act: -0.1700
Data Index: 2504804 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3175. Min Range: -7.3175
Max Act: 6.8175. Min Act: -0.1700
Data Index: 5362746 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3175. Min Range: -7.3175
Max Act: 6.7862. Min Act: -0.1700
Data Index: 4093257 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3175. Min Range: -7.3175
Max Act: 6.7862. Min Act: -0.1700
Data Index: 8732431 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3175. Min Range: -7.3175
Max Act: 6.7862. Min Act: -0.1700
Data Index: 121762 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3175. Min Range: -7.3175
Max Act: 6.7237. Min Act: -0.1700
Data Index: 4170169 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3175. Min Range: -7.3175
Max Act: 6.7550. Min Act: -0.1700
Data Index: 8106806 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3175. Min Range: -7.3175
Max Act: 6.7862. Min Act: -0.1700
Data Index: 7714628 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3175. Min Range: -7.3175
Max Act: 6.7237. Min Act: -0.1700
Data Index: 249628 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19