Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2315 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5538. Min Range: -3.5538
Max Act: 3.5538. Min Act: -0.1700
Data Index: 7639018 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5538. Min Range: -3.5538
Max Act: 3.5224. Min Act: -0.1700
Data Index: 1027876 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5538. Min Range: -3.5538
Max Act: 3.4128. Min Act: -0.1700
Data Index: 5841362 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5538. Min Range: -3.5538
Max Act: 3.3971. Min Act: -0.1700
Data Index: 4276948 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5538. Min Range: -3.5538
Max Act: 3.3814. Min Act: -0.1700
Data Index: 3104374 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5538. Min Range: -3.5538
Max Act: 3.3187. Min Act: -0.1700
Data Index: 776173 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5538. Min Range: -3.5538
Max Act: 3.2873. Min Act: -0.1700
Data Index: 366335 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5538. Min Range: -3.5538
Max Act: 3.2873. Min Act: -0.1700
Data Index: 935161 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5538. Min Range: -3.5538
Max Act: 3.2873. Min Act: -0.1700
Data Index: 7699151 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5538. Min Range: -3.5538
Max Act: 3.2401. Min Act: -0.1700
Data Index: 1737214 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5538. Min Range: -3.5538
Max Act: 3.2559. Min Act: -0.1700
Data Index: 7527832 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5538. Min Range: -3.5538
Max Act: 3.2401. Min Act: -0.1700
Data Index: 6523966 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5538. Min Range: -3.5538
Max Act: 3.2401. Min Act: -0.1700
Data Index: 1205743 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5538. Min Range: -3.5538
Max Act: 3.2401. Min Act: -0.1700
Data Index: 4619688 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5538. Min Range: -3.5538
Max Act: 3.2244. Min Act: -0.1700
Data Index: 1854952 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5538. Min Range: -3.5538
Max Act: 3.2559. Min Act: -0.1700
Data Index: 4104789 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5538. Min Range: -3.5538
Max Act: 3.2401. Min Act: -0.1700
Data Index: 5458696 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5538. Min Range: -3.5538
Max Act: 3.2244. Min Act: -0.1700
Data Index: 3355532 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5538. Min Range: -3.5538
Max Act: 3.2244. Min Act: -0.1700
Data Index: 5350833 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5538. Min Range: -3.5538
Max Act: 3.2087. Min Act: -0.1700
Data Index: 922928 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19