Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5644 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8617. Min Range: -4.8617
Max Act: 4.8617. Min Act: -0.1700
Data Index: 486844 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8617. Min Range: -4.8617
Max Act: 4.8617. Min Act: -0.1700
Data Index: 1456240 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8617. Min Range: -4.8617
Max Act: 4.8305. Min Act: -0.1699
Data Index: 987995 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8617. Min Range: -4.8617
Max Act: 4.7992. Min Act: -0.1700
Data Index: 7828726 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8617. Min Range: -4.8617
Max Act: 4.7680. Min Act: -0.1700
Data Index: 309987 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8617. Min Range: -4.8617
Max Act: 4.7992. Min Act: -0.1700
Data Index: 7107923 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8617. Min Range: -4.8617
Max Act: 4.7992. Min Act: -0.1700
Data Index: 6318678 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8617. Min Range: -4.8617
Max Act: 4.7992. Min Act: -0.1700
Data Index: 1441116 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8617. Min Range: -4.8617
Max Act: 4.7680. Min Act: -0.1700
Data Index: 1056863 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8617. Min Range: -4.8617
Max Act: 4.7680. Min Act: -0.1700
Data Index: 7052154 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8617. Min Range: -4.8617
Max Act: 4.7680. Min Act: -0.1700
Data Index: 4747820 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8617. Min Range: -4.8617
Max Act: 4.7680. Min Act: -0.1700
Data Index: 4723528 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8617. Min Range: -4.8617
Max Act: 4.7367. Min Act: -0.1700
Data Index: 2488498 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8617. Min Range: -4.8617
Max Act: 4.7367. Min Act: -0.1700
Data Index: 6632873 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8617. Min Range: -4.8617
Max Act: 4.7367. Min Act: -0.1700
Data Index: 4462597 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8617. Min Range: -4.8617
Max Act: 4.7367. Min Act: -0.1700
Data Index: 2059427 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8617. Min Range: -4.8617
Max Act: 4.7055. Min Act: -0.1700
Data Index: 1198717 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8617. Min Range: -4.8617
Max Act: 4.7055. Min Act: -0.1700
Data Index: 5432218 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8617. Min Range: -4.8617
Max Act: 4.7055. Min Act: -0.1700
Data Index: 5270618 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8617. Min Range: -4.8617
Max Act: 4.6742. Min Act: -0.1700
Data Index: 6868847 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19