Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1355 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5969. Min Range: -3.5969
Max Act: 3.5969. Min Act: -0.1700
Data Index: 385767 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5969. Min Range: -3.5969
Max Act: 3.5656. Min Act: -0.1700
Data Index: 6257696 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5969. Min Range: -3.5969
Max Act: 3.5656. Min Act: -0.1700
Data Index: 4182578 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5969. Min Range: -3.5969
Max Act: 3.5499. Min Act: -0.1700
Data Index: 3344757 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5969. Min Range: -3.5969
Max Act: 3.5499. Min Act: -0.1700
Data Index: 3473264 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5969. Min Range: -3.5969
Max Act: 3.4403. Min Act: -0.1700
Data Index: 2420761 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5969. Min Range: -3.5969
Max Act: 3.4559. Min Act: -0.1700
Data Index: 920812 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5969. Min Range: -3.5969
Max Act: 3.4559. Min Act: -0.1700
Data Index: 4872436 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5969. Min Range: -3.5969
Max Act: 3.4559. Min Act: -0.1700
Data Index: 8552826 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5969. Min Range: -3.5969
Max Act: 3.4559. Min Act: -0.1700
Data Index: 808422 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5969. Min Range: -3.5969
Max Act: 3.4403. Min Act: -0.1700
Data Index: 7017942 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5969. Min Range: -3.5969
Max Act: 3.4559. Min Act: -0.1700
Data Index: 7210448 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5969. Min Range: -3.5969
Max Act: 3.4403. Min Act: -0.1700
Data Index: 4981727 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5969. Min Range: -3.5969
Max Act: 3.4089. Min Act: -0.1700
Data Index: 8216049 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5969. Min Range: -3.5969
Max Act: 3.4089. Min Act: -0.1700
Data Index: 6337494 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5969. Min Range: -3.5969
Max Act: 3.3932. Min Act: -0.1700
Data Index: 5817354 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5969. Min Range: -3.5969
Max Act: 3.3932. Min Act: -0.1700
Data Index: 4842721 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5969. Min Range: -3.5969
Max Act: 3.4089. Min Act: -0.1700
Data Index: 2117599 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5969. Min Range: -3.5969
Max Act: 3.3932. Min Act: -0.1700
Data Index: 7109650 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5969. Min Range: -3.5969
Max Act: 3.3619. Min Act: -0.1700
Data Index: 5135254 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19