Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3623 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9215. Min Range: -5.9215
Max Act: 5.9215. Min Act: -0.1700
Data Index: 4605904 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9215. Min Range: -5.9215
Max Act: 5.7653. Min Act: -0.1700
Data Index: 6954702 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9215. Min Range: -5.9215
Max Act: 5.6715. Min Act: -0.1700
Data Index: 4933994 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9215. Min Range: -5.9215
Max Act: 5.5465. Min Act: -0.1700
Data Index: 2702989 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9215. Min Range: -5.9215
Max Act: 5.4528. Min Act: -0.1700
Data Index: 2829777 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9215. Min Range: -5.9215
Max Act: 5.3590. Min Act: -0.1700
Data Index: 5284923 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9215. Min Range: -5.9215
Max Act: 5.3590. Min Act: -0.1700
Data Index: 5077004 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9215. Min Range: -5.9215
Max Act: 5.2965. Min Act: -0.1700
Data Index: 8536511 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9215. Min Range: -5.9215
Max Act: 5.2965. Min Act: -0.1700
Data Index: 954413 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9215. Min Range: -5.9215
Max Act: 5.2965. Min Act: -0.1700
Data Index: 7304341 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9215. Min Range: -5.9215
Max Act: 5.2653. Min Act: -0.1700
Data Index: 8355810 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9215. Min Range: -5.9215
Max Act: 5.2965. Min Act: -0.1700
Data Index: 3096505 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9215. Min Range: -5.9215
Max Act: 5.2340. Min Act: -0.1700
Data Index: 3280924 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9215. Min Range: -5.9215
Max Act: 5.2340. Min Act: -0.1700
Data Index: 1425084 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9215. Min Range: -5.9215
Max Act: 5.2653. Min Act: -0.1700
Data Index: 8660497 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9215. Min Range: -5.9215
Max Act: 5.2028. Min Act: -0.1700
Data Index: 7138033 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9215. Min Range: -5.9215
Max Act: 5.2028. Min Act: -0.1700
Data Index: 5538689 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9215. Min Range: -5.9215
Max Act: 5.2340. Min Act: -0.1700
Data Index: 149993 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9215. Min Range: -5.9215
Max Act: 5.2028. Min Act: -0.1700
Data Index: 5208588 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9215. Min Range: -5.9215
Max Act: 5.2028. Min Act: -0.1700
Data Index: 6409270 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19