Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 845 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5411. Min Range: -2.5411
Max Act: 2.5411. Min Act: -0.1700
Data Index: 4574315 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5411. Min Range: -2.5411
Max Act: 2.4925. Min Act: -0.1700
Data Index: 4322488 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5411. Min Range: -2.5411
Max Act: 2.4763. Min Act: -0.1700
Data Index: 7152506 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5411. Min Range: -2.5411
Max Act: 2.4601. Min Act: -0.1700
Data Index: 5763445 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5411. Min Range: -2.5411
Max Act: 2.4601. Min Act: -0.1700
Data Index: 3998947 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5411. Min Range: -2.5411
Max Act: 2.4438. Min Act: -0.1700
Data Index: 6045294 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5411. Min Range: -2.5411
Max Act: 2.4112. Min Act: -0.1700
Data Index: 2696593 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5411. Min Range: -2.5411
Max Act: 2.3949. Min Act: -0.1700
Data Index: 3998945 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5411. Min Range: -2.5411
Max Act: 2.3786. Min Act: -0.1700
Data Index: 1724957 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5411. Min Range: -2.5411
Max Act: 2.3622. Min Act: -0.1700
Data Index: 2654645 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5411. Min Range: -2.5411
Max Act: 2.3294. Min Act: -0.1700
Data Index: 5702989 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5411. Min Range: -2.5411
Max Act: 2.3458. Min Act: -0.1700
Data Index: 7409924 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5411. Min Range: -2.5411
Max Act: 2.3458. Min Act: -0.1700
Data Index: 4564464 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5411. Min Range: -2.5411
Max Act: 2.3294. Min Act: -0.1700
Data Index: 6814826 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5411. Min Range: -2.5411
Max Act: 2.3294. Min Act: -0.1700
Data Index: 7864113 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5411. Min Range: -2.5411
Max Act: 2.3294. Min Act: -0.1700
Data Index: 3416418 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5411. Min Range: -2.5411
Max Act: 2.3130. Min Act: -0.1700
Data Index: 1359952 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5411. Min Range: -2.5411
Max Act: 2.3294. Min Act: -0.1700
Data Index: 4266452 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5411. Min Range: -2.5411
Max Act: 2.3130. Min Act: -0.1700
Data Index: 2654644 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5411. Min Range: -2.5411
Max Act: 2.3130. Min Act: -0.1700
Data Index: 4803149 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19