Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2292 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6822. Min Range: -8.6822
Max Act: 8.6822. Min Act: -0.1700
Data Index: 2201071 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6822. Min Range: -8.6822
Max Act: 8.2447. Min Act: -0.1700
Data Index: 8734067 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6822. Min Range: -8.6822
Max Act: 8.3072. Min Act: -0.1700
Data Index: 6152673 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6822. Min Range: -8.6822
Max Act: 8.2447. Min Act: -0.1700
Data Index: 4432329 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6822. Min Range: -8.6822
Max Act: 8.2447. Min Act: -0.1700
Data Index: 5341158 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6822. Min Range: -8.6822
Max Act: 8.1822. Min Act: -0.1700
Data Index: 8619425 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6822. Min Range: -8.6822
Max Act: 8.1822. Min Act: -0.1700
Data Index: 5096904 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6822. Min Range: -8.6822
Max Act: 8.1197. Min Act: -0.1700
Data Index: 6985840 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6822. Min Range: -8.6822
Max Act: 8.1197. Min Act: -0.1700
Data Index: 7531537 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6822. Min Range: -8.6822
Max Act: 8.0572. Min Act: -0.1700
Data Index: 4332297 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6822. Min Range: -8.6822
Max Act: 8.0260. Min Act: -0.1700
Data Index: 2724376 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6822. Min Range: -8.6822
Max Act: 8.0260. Min Act: -0.1700
Data Index: 1906953 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6822. Min Range: -8.6822
Max Act: 7.9635. Min Act: -0.1700
Data Index: 6291515 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6822. Min Range: -8.6822
Max Act: 7.9947. Min Act: -0.1700
Data Index: 960352 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6822. Min Range: -8.6822
Max Act: 7.9947. Min Act: -0.1700
Data Index: 8778507 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6822. Min Range: -8.6822
Max Act: 7.9947. Min Act: -0.1700
Data Index: 4524614 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6822. Min Range: -8.6822
Max Act: 7.9635. Min Act: -0.1700
Data Index: 299824 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6822. Min Range: -8.6822
Max Act: 7.9635. Min Act: -0.1700
Data Index: 2818270 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6822. Min Range: -8.6822
Max Act: 7.9635. Min Act: -0.1700
Data Index: 69674 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6822. Min Range: -8.6822
Max Act: 7.9635. Min Act: -0.1700
Data Index: 5441390 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19