Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5005 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2580. Min Range: -8.2580
Max Act: 8.2580. Min Act: -0.1700
Data Index: 6839810 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.8830. Min Act: -0.1700
Data Index: 1397566 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.9455. Min Act: -0.1700
Data Index: 6949038 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.8830. Min Act: -0.1700
Data Index: 5235057 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.7893. Min Act: -0.1700
Data Index: 4089030 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.7893. Min Act: -0.1700
Data Index: 7325297 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.7268. Min Act: -0.1700
Data Index: 8033214 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.6955. Min Act: -0.1700
Data Index: 1207235 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.6643. Min Act: -0.1700
Data Index: 5003795 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.6330. Min Act: -0.1700
Data Index: 47989 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.6643. Min Act: -0.1700
Data Index: 3537755 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.6330. Min Act: -0.1700
Data Index: 8442457 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.6018. Min Act: -0.1700
Data Index: 8161968 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.5705. Min Act: -0.1700
Data Index: 8543939 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.5393. Min Act: -0.1700
Data Index: 3854914 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.5393. Min Act: -0.1700
Data Index: 4125500 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.5080. Min Act: -0.1700
Data Index: 2556187 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.5080. Min Act: -0.1700
Data Index: 1042122 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.5080. Min Act: -0.1700
Data Index: 6113420 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.4768. Min Act: -0.1700
Data Index: 5556229 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19