Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 742 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.8720. Min Act: -0.1700
Data Index: 8782561 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.6220. Min Act: -0.1700
Data Index: 2702681 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.6220. Min Act: -0.1700
Data Index: 8464143 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.5908. Min Act: -0.1700
Data Index: 6334198 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.5908. Min Act: -0.1700
Data Index: 7156721 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.5283. Min Act: -0.1700
Data Index: 5764160 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.5283. Min Act: -0.1700
Data Index: 4417026 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.4658. Min Act: -0.1700
Data Index: 3073668 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.4658. Min Act: -0.1700
Data Index: 4493060 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.4345. Min Act: -0.1700
Data Index: 8041649 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.4345. Min Act: -0.1700
Data Index: 2702676 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.4345. Min Act: -0.1700
Data Index: 8486407 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.4033. Min Act: -0.1700
Data Index: 5785939 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.4345. Min Act: -0.1700
Data Index: 404364 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.4345. Min Act: -0.1700
Data Index: 5544005 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.4658. Min Act: -0.1700
Data Index: 6483746 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.4033. Min Act: -0.1700
Data Index: 5663353 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.4033. Min Act: -0.1700
Data Index: 3066301 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.3408. Min Act: -0.1700
Data Index: 5011948 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.3720. Min Act: -0.1700
Data Index: 5274648 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19