Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2875 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7230. Min Range: -6.7230
Max Act: 6.7230. Min Act: -0.1700
Data Index: 5753802 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7230. Min Range: -6.7230
Max Act: 6.3480. Min Act: -0.1700
Data Index: 7858536 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7230. Min Range: -6.7230
Max Act: 6.2855. Min Act: -0.1700
Data Index: 4723308 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7230. Min Range: -6.7230
Max Act: 6.2230. Min Act: -0.1700
Data Index: 5753803 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7230. Min Range: -6.7230
Max Act: 6.2230. Min Act: -0.1700
Data Index: 7831018 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7230. Min Range: -6.7230
Max Act: 6.2230. Min Act: -0.1700
Data Index: 1327442 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7230. Min Range: -6.7230
Max Act: 6.1605. Min Act: -0.1700
Data Index: 7565476 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7230. Min Range: -6.7230
Max Act: 6.1605. Min Act: -0.1700
Data Index: 5815150 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7230. Min Range: -6.7230
Max Act: 6.1605. Min Act: -0.1700
Data Index: 6897722 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7230. Min Range: -6.7230
Max Act: 6.0668. Min Act: -0.1700
Data Index: 2186818 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7230. Min Range: -6.7230
Max Act: 6.0668. Min Act: -0.1700
Data Index: 2270861 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7230. Min Range: -6.7230
Max Act: 6.0668. Min Act: -0.1700
Data Index: 4369085 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7230. Min Range: -6.7230
Max Act: 6.0355. Min Act: -0.1700
Data Index: 87769 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7230. Min Range: -6.7230
Max Act: 6.0043. Min Act: -0.1700
Data Index: 4860805 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7230. Min Range: -6.7230
Max Act: 6.0043. Min Act: -0.1700
Data Index: 3634284 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7230. Min Range: -6.7230
Max Act: 5.9730. Min Act: -0.1700
Data Index: 6600020 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7230. Min Range: -6.7230
Max Act: 5.9730. Min Act: -0.1700
Data Index: 5633319 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7230. Min Range: -6.7230
Max Act: 6.0043. Min Act: -0.1700
Data Index: 484498 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7230. Min Range: -6.7230
Max Act: 5.9418. Min Act: -0.1700
Data Index: 4501836 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7230. Min Range: -6.7230
Max Act: 5.9105. Min Act: -0.1700
Data Index: 4250136 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19