Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3290 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2467. Min Range: -7.2467
Max Act: 7.2467. Min Act: -0.1700
Data Index: 5350885 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2467. Min Range: -7.2467
Max Act: 6.9967. Min Act: -0.1700
Data Index: 4409304 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2467. Min Range: -7.2467
Max Act: 6.9654. Min Act: -0.1700
Data Index: 8556940 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2467. Min Range: -7.2467
Max Act: 6.8404. Min Act: -0.1700
Data Index: 4485030 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2467. Min Range: -7.2467
Max Act: 6.8092. Min Act: -0.1700
Data Index: 5081408 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2467. Min Range: -7.2467
Max Act: 6.8092. Min Act: -0.1700
Data Index: 2862659 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2467. Min Range: -7.2467
Max Act: 6.7467. Min Act: -0.1700
Data Index: 8116894 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2467. Min Range: -7.2467
Max Act: 6.6842. Min Act: -0.1700
Data Index: 3036036 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2467. Min Range: -7.2467
Max Act: 6.7154. Min Act: -0.1700
Data Index: 671264 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2467. Min Range: -7.2467
Max Act: 6.7154. Min Act: -0.1700
Data Index: 5508681 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2467. Min Range: -7.2467
Max Act: 6.6842. Min Act: -0.1700
Data Index: 867931 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2467. Min Range: -7.2467
Max Act: 6.6842. Min Act: -0.1700
Data Index: 7540659 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2467. Min Range: -7.2467
Max Act: 6.6842. Min Act: -0.1700
Data Index: 5726163 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2467. Min Range: -7.2467
Max Act: 6.6529. Min Act: -0.1700
Data Index: 3767725 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2467. Min Range: -7.2467
Max Act: 6.5904. Min Act: -0.1700
Data Index: 8543769 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2467. Min Range: -7.2467
Max Act: 6.6217. Min Act: -0.1700
Data Index: 451650 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2467. Min Range: -7.2467
Max Act: 6.5904. Min Act: -0.1700
Data Index: 651421 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2467. Min Range: -7.2467
Max Act: 6.5592. Min Act: -0.1700
Data Index: 275593 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2467. Min Range: -7.2467
Max Act: 6.5592. Min Act: -0.1700
Data Index: 5711469 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2467. Min Range: -7.2467
Max Act: 6.5904. Min Act: -0.1700
Data Index: 5555579 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19