Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3966 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5342. Min Range: -3.5342
Max Act: 3.5342. Min Act: -0.1700
Data Index: 63824 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5342. Min Range: -3.5342
Max Act: 3.4715. Min Act: -0.1700
Data Index: 795268 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5342. Min Range: -3.5342
Max Act: 3.3775. Min Act: -0.1700
Data Index: 5381032 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5342. Min Range: -3.5342
Max Act: 3.3775. Min Act: -0.1700
Data Index: 6923252 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5342. Min Range: -3.5342
Max Act: 3.3461. Min Act: -0.1700
Data Index: 906653 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5342. Min Range: -3.5342
Max Act: 3.3304. Min Act: -0.1700
Data Index: 2502132 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5342. Min Range: -3.5342
Max Act: 3.3304. Min Act: -0.1700
Data Index: 851088 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5342. Min Range: -3.5342
Max Act: 3.3304. Min Act: -0.1700
Data Index: 876484 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5342. Min Range: -3.5342
Max Act: 3.3147. Min Act: -0.1700
Data Index: 8606351 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5342. Min Range: -3.5342
Max Act: 3.3147. Min Act: -0.1700
Data Index: 1255196 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5342. Min Range: -3.5342
Max Act: 3.3147. Min Act: -0.1700
Data Index: 5884211 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5342. Min Range: -3.5342
Max Act: 3.3147. Min Act: -0.1700
Data Index: 8002286 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5342. Min Range: -3.5342
Max Act: 3.2833. Min Act: -0.1700
Data Index: 8125116 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5342. Min Range: -3.5342
Max Act: 3.2833. Min Act: -0.1700
Data Index: 7535585 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5342. Min Range: -3.5342
Max Act: 3.2833. Min Act: -0.1700
Data Index: 2516766 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5342. Min Range: -3.5342
Max Act: 3.2676. Min Act: -0.1700
Data Index: 4571975 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5342. Min Range: -3.5342
Max Act: 3.2676. Min Act: -0.1700
Data Index: 4573146 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5342. Min Range: -3.5342
Max Act: 3.2833. Min Act: -0.1700
Data Index: 2461827 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5342. Min Range: -3.5342
Max Act: 3.2676. Min Act: -0.1700
Data Index: 3786252 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5342. Min Range: -3.5342
Max Act: 3.2676. Min Act: -0.1700
Data Index: 7555744 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19