Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6358 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5164. Min Range: -5.5164
Max Act: 5.5164. Min Act: -0.1700
Data Index: 2918391 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5164. Min Range: -5.5164
Max Act: 5.3289. Min Act: -0.1700
Data Index: 4560564 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5164. Min Range: -5.5164
Max Act: 5.3289. Min Act: -0.1700
Data Index: 4789177 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5164. Min Range: -5.5164
Max Act: 5.2977. Min Act: -0.1700
Data Index: 462149 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5164. Min Range: -5.5164
Max Act: 5.2664. Min Act: -0.1700
Data Index: 1672370 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5164. Min Range: -5.5164
Max Act: 5.2352. Min Act: -0.1700
Data Index: 3318712 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5164. Min Range: -5.5164
Max Act: 5.2352. Min Act: -0.1700
Data Index: 8324978 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5164. Min Range: -5.5164
Max Act: 5.2039. Min Act: -0.1700
Data Index: 8413035 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5164. Min Range: -5.5164
Max Act: 5.2352. Min Act: -0.1700
Data Index: 59399 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5164. Min Range: -5.5164
Max Act: 5.2352. Min Act: -0.1700
Data Index: 6511210 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5164. Min Range: -5.5164
Max Act: 5.2039. Min Act: -0.1700
Data Index: 841668 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5164. Min Range: -5.5164
Max Act: 5.2039. Min Act: -0.1700
Data Index: 6414247 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5164. Min Range: -5.5164
Max Act: 5.2039. Min Act: -0.1700
Data Index: 1024538 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5164. Min Range: -5.5164
Max Act: 5.1414. Min Act: -0.1700
Data Index: 7136819 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5164. Min Range: -5.5164
Max Act: 5.1727. Min Act: -0.1700
Data Index: 1733229 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5164. Min Range: -5.5164
Max Act: 5.1727. Min Act: -0.1700
Data Index: 3042156 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5164. Min Range: -5.5164
Max Act: 5.1727. Min Act: -0.1700
Data Index: 2321533 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5164. Min Range: -5.5164
Max Act: 5.1727. Min Act: -0.1700
Data Index: 6424927 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5164. Min Range: -5.5164
Max Act: 5.1727. Min Act: -0.1700
Data Index: 7000925 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5164. Min Range: -5.5164
Max Act: 5.1727. Min Act: -0.1700
Data Index: 6925138 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19