Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1480 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5648. Min Range: -3.5648
Max Act: 3.5648. Min Act: -0.1700
Data Index: 4189763 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5648. Min Range: -3.5648
Max Act: 3.5648. Min Act: -0.1700
Data Index: 996410 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5648. Min Range: -3.5648
Max Act: 3.5335. Min Act: -0.1700
Data Index: 4217356 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5648. Min Range: -3.5648
Max Act: 3.5022. Min Act: -0.1700
Data Index: 1335958 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5648. Min Range: -3.5648
Max Act: 3.4708. Min Act: -0.1700
Data Index: 5601312 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5648. Min Range: -3.5648
Max Act: 3.5022. Min Act: -0.1700
Data Index: 716971 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5648. Min Range: -3.5648
Max Act: 3.4708. Min Act: -0.1700
Data Index: 6057431 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5648. Min Range: -3.5648
Max Act: 3.5022. Min Act: -0.1700
Data Index: 2621364 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5648. Min Range: -3.5648
Max Act: 3.5022. Min Act: -0.1700
Data Index: 3855274 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5648. Min Range: -3.5648
Max Act: 3.5022. Min Act: -0.1700
Data Index: 540378 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5648. Min Range: -3.5648
Max Act: 3.4708. Min Act: -0.1700
Data Index: 163 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5648. Min Range: -3.5648
Max Act: 3.4708. Min Act: -0.1700
Data Index: 1042574 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5648. Min Range: -3.5648
Max Act: 3.4708. Min Act: -0.1700
Data Index: 981258 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5648. Min Range: -3.5648
Max Act: 3.4708. Min Act: -0.1700
Data Index: 3028240 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5648. Min Range: -3.5648
Max Act: 3.4708. Min Act: -0.1700
Data Index: 5474648 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5648. Min Range: -3.5648
Max Act: 3.4708. Min Act: -0.1700
Data Index: 660558 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5648. Min Range: -3.5648
Max Act: 3.4081. Min Act: -0.1700
Data Index: 3305278 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5648. Min Range: -3.5648
Max Act: 3.4395. Min Act: -0.1700
Data Index: 3641890 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5648. Min Range: -3.5648
Max Act: 3.4395. Min Act: -0.1700
Data Index: 2213633 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5648. Min Range: -3.5648
Max Act: 3.4395. Min Act: -0.1700
Data Index: 3151724 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19