Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3107 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1177. Min Range: -5.1177
Max Act: 5.1177. Min Act: -0.1700
Data Index: 8395319 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1177. Min Range: -5.1177
Max Act: 5.0240. Min Act: -0.1700
Data Index: 3892310 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1177. Min Range: -5.1177
Max Act: 4.9927. Min Act: -0.1700
Data Index: 8346163 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1177. Min Range: -5.1177
Max Act: 4.9302. Min Act: -0.1700
Data Index: 1897260 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1177. Min Range: -5.1177
Max Act: 4.8990. Min Act: -0.1700
Data Index: 4745620 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1177. Min Range: -5.1177
Max Act: 4.9302. Min Act: -0.1700
Data Index: 5663641 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1177. Min Range: -5.1177
Max Act: 4.8990. Min Act: -0.1700
Data Index: 3429641 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1177. Min Range: -5.1177
Max Act: 4.8990. Min Act: -0.1700
Data Index: 3837827 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1177. Min Range: -5.1177
Max Act: 4.8990. Min Act: -0.1700
Data Index: 3908206 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1177. Min Range: -5.1177
Max Act: 4.8990. Min Act: -0.1700
Data Index: 6237726 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1177. Min Range: -5.1177
Max Act: 4.9302. Min Act: -0.1700
Data Index: 7108411 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1177. Min Range: -5.1177
Max Act: 4.8990. Min Act: -0.1700
Data Index: 450693 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1177. Min Range: -5.1177
Max Act: 4.8677. Min Act: -0.1700
Data Index: 4646170 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1177. Min Range: -5.1177
Max Act: 4.8677. Min Act: -0.1700
Data Index: 137713 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1177. Min Range: -5.1177
Max Act: 4.8677. Min Act: -0.1700
Data Index: 4101418 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1177. Min Range: -5.1177
Max Act: 4.8365. Min Act: -0.1700
Data Index: 7223616 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1177. Min Range: -5.1177
Max Act: 4.8365. Min Act: -0.1700
Data Index: 848304 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1177. Min Range: -5.1177
Max Act: 4.8365. Min Act: -0.1700
Data Index: 1037417 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1177. Min Range: -5.1177
Max Act: 4.8052. Min Act: -0.1700
Data Index: 837456 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1177. Min Range: -5.1177
Max Act: 4.8365. Min Act: -0.1700
Data Index: 6769662 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19