Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2894 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1033. Min Range: -3.1033
Max Act: 3.1033. Min Act: -0.1700
Data Index: 7500087 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1033. Min Range: -3.1033
Max Act: 3.1033. Min Act: -0.1700
Data Index: 2324485 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1033. Min Range: -3.1033
Max Act: 3.0875. Min Act: -0.1700
Data Index: 4555317 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1033. Min Range: -3.1033
Max Act: 3.0560. Min Act: -0.1700
Data Index: 6019791 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1033. Min Range: -3.1033
Max Act: 3.0560. Min Act: -0.1700
Data Index: 1475881 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1033. Min Range: -3.1033
Max Act: 3.0560. Min Act: -0.1700
Data Index: 5092848 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1033. Min Range: -3.1033
Max Act: 3.0086. Min Act: -0.1700
Data Index: 7305048 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1033. Min Range: -3.1033
Max Act: 3.0086. Min Act: -0.1700
Data Index: 2037453 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1033. Min Range: -3.1033
Max Act: 3.0244. Min Act: -0.1700
Data Index: 1849749 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1033. Min Range: -3.1033
Max Act: 2.9928. Min Act: -0.1700
Data Index: 2265342 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1033. Min Range: -3.1033
Max Act: 3.0086. Min Act: -0.1700
Data Index: 7584951 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1033. Min Range: -3.1033
Max Act: 2.9770. Min Act: -0.1700
Data Index: 3468971 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1033. Min Range: -3.1033
Max Act: 2.9928. Min Act: -0.1700
Data Index: 755475 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1033. Min Range: -3.1033
Max Act: 2.9770. Min Act: -0.1700
Data Index: 5800703 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1033. Min Range: -3.1033
Max Act: 2.9770. Min Act: -0.1700
Data Index: 2386699 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1033. Min Range: -3.1033
Max Act: 2.9612. Min Act: -0.1700
Data Index: 6258803 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1033. Min Range: -3.1033
Max Act: 2.9612. Min Act: -0.1700
Data Index: 1656552 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1033. Min Range: -3.1033
Max Act: 2.9453. Min Act: -0.1700
Data Index: 5834990 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1033. Min Range: -3.1033
Max Act: 2.9612. Min Act: -0.1700
Data Index: 5711538 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1033. Min Range: -3.1033
Max Act: 2.9453. Min Act: -0.1700
Data Index: 938317 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19