Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 602 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9509. Min Range: -5.9509
Max Act: 5.9509. Min Act: -0.1700
Data Index: 2112884 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9509. Min Range: -5.9509
Max Act: 5.8884. Min Act: -0.1700
Data Index: 6458773 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9509. Min Range: -5.9509
Max Act: 5.7946. Min Act: -0.1700
Data Index: 2112885 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9509. Min Range: -5.9509
Max Act: 5.6384. Min Act: -0.1700
Data Index: 4474494 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9509. Min Range: -5.9509
Max Act: 5.6384. Min Act: -0.1700
Data Index: 2851255 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9509. Min Range: -5.9509
Max Act: 5.5759. Min Act: -0.1700
Data Index: 1397493 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9509. Min Range: -5.9509
Max Act: 5.6071. Min Act: -0.1700
Data Index: 622454 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9509. Min Range: -5.9509
Max Act: 5.5446. Min Act: -0.1700
Data Index: 2851256 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9509. Min Range: -5.9509
Max Act: 5.3884. Min Act: -0.1700
Data Index: 4884180 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9509. Min Range: -5.9509
Max Act: 5.3259. Min Act: -0.1700
Data Index: 7998164 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9509. Min Range: -5.9509
Max Act: 5.2946. Min Act: -0.1700
Data Index: 4502083 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9509. Min Range: -5.9509
Max Act: 5.2946. Min Act: -0.1700
Data Index: 779502 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9509. Min Range: -5.9509
Max Act: 5.2946. Min Act: -0.1700
Data Index: 856022 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9509. Min Range: -5.9509
Max Act: 5.2946. Min Act: -0.1700
Data Index: 2204850 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9509. Min Range: -5.9509
Max Act: 5.2946. Min Act: -0.1700
Data Index: 2768380 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9509. Min Range: -5.9509
Max Act: 5.2634. Min Act: -0.1700
Data Index: 2342508 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9509. Min Range: -5.9509
Max Act: 5.2634. Min Act: -0.1700
Data Index: 1973690 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9509. Min Range: -5.9509
Max Act: 5.2946. Min Act: -0.1700
Data Index: 3713758 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9509. Min Range: -5.9509
Max Act: 5.2634. Min Act: -0.1700
Data Index: 8203814 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9509. Min Range: -5.9509
Max Act: 5.2321. Min Act: -0.1700
Data Index: 7837626 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19