Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3024 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3395. Min Range: -3.3395
Max Act: 3.3395. Min Act: -0.1700
Data Index: 4150610 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3395. Min Range: -3.3395
Max Act: 3.3395. Min Act: -0.1700
Data Index: 1443961 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3395. Min Range: -3.3395
Max Act: 3.3395. Min Act: -0.1700
Data Index: 8785250 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3395. Min Range: -3.3395
Max Act: 3.3081. Min Act: -0.1700
Data Index: 6698434 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3395. Min Range: -3.3395
Max Act: 3.2453. Min Act: -0.1700
Data Index: 4559520 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3395. Min Range: -3.3395
Max Act: 3.2139. Min Act: -0.1700
Data Index: 5699249 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3395. Min Range: -3.3395
Max Act: 3.2139. Min Act: -0.1700
Data Index: 5718174 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3395. Min Range: -3.3395
Max Act: 3.2139. Min Act: -0.1700
Data Index: 1949718 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3395. Min Range: -3.3395
Max Act: 3.2139. Min Act: -0.1700
Data Index: 8444943 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3395. Min Range: -3.3395
Max Act: 3.1824. Min Act: -0.1700
Data Index: 442144 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3395. Min Range: -3.3395
Max Act: 3.1824. Min Act: -0.1700
Data Index: 227030 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3395. Min Range: -3.3395
Max Act: 3.1824. Min Act: -0.1700
Data Index: 3638835 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3395. Min Range: -3.3395
Max Act: 3.1824. Min Act: -0.1700
Data Index: 2874870 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3395. Min Range: -3.3395
Max Act: 3.1824. Min Act: -0.1700
Data Index: 7921986 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3395. Min Range: -3.3395
Max Act: 3.1824. Min Act: -0.1700
Data Index: 7665208 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3395. Min Range: -3.3395
Max Act: 3.1824. Min Act: -0.1700
Data Index: 981743 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3395. Min Range: -3.3395
Max Act: 3.1824. Min Act: -0.1700
Data Index: 6077280 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3395. Min Range: -3.3395
Max Act: 3.1824. Min Act: -0.1700
Data Index: 5007270 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3395. Min Range: -3.3395
Max Act: 3.1510. Min Act: -0.1700
Data Index: 90989 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3395. Min Range: -3.3395
Max Act: 3.1510. Min Act: -0.1700
Data Index: 3022768 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19