Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 905 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3662. Min Range: -4.3662
Max Act: 4.3662. Min Act: -0.1700
Data Index: 5912002 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3662. Min Range: -4.3662
Max Act: 4.3662. Min Act: -0.1700
Data Index: 4517024 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3662. Min Range: -4.3662
Max Act: 4.3349. Min Act: -0.1699
Data Index: 8578959 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3662. Min Range: -4.3662
Max Act: 4.3349. Min Act: -0.1700
Data Index: 1297832 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3662. Min Range: -4.3662
Max Act: 4.3037. Min Act: -0.1700
Data Index: 4787626 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3662. Min Range: -4.3662
Max Act: 4.3037. Min Act: -0.1700
Data Index: 6003206 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3662. Min Range: -4.3662
Max Act: 4.3037. Min Act: -0.1700
Data Index: 2353654 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3662. Min Range: -4.3662
Max Act: 4.3037. Min Act: -0.1700
Data Index: 1354657 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3662. Min Range: -4.3662
Max Act: 4.3037. Min Act: -0.1700
Data Index: 7034332 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3662. Min Range: -4.3662
Max Act: 4.3037. Min Act: -0.1699
Data Index: 6818827 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3662. Min Range: -4.3662
Max Act: 4.3349. Min Act: -0.1700
Data Index: 6023444 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3662. Min Range: -4.3662
Max Act: 4.3037. Min Act: -0.1700
Data Index: 4285287 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3662. Min Range: -4.3662
Max Act: 4.3037. Min Act: -0.1700
Data Index: 3931495 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3662. Min Range: -4.3662
Max Act: 4.2724. Min Act: -0.1700
Data Index: 2100140 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3662. Min Range: -4.3662
Max Act: 4.2724. Min Act: -0.1700
Data Index: 2234425 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3662. Min Range: -4.3662
Max Act: 4.2412. Min Act: -0.1700
Data Index: 2327733 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3662. Min Range: -4.3662
Max Act: 4.2724. Min Act: -0.1700
Data Index: 5911903 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3662. Min Range: -4.3662
Max Act: 4.2724. Min Act: -0.1700
Data Index: 1514239 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3662. Min Range: -4.3662
Max Act: 4.2724. Min Act: -0.1700
Data Index: 297476 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3662. Min Range: -4.3662
Max Act: 4.2724. Min Act: -0.1700
Data Index: 388888 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19