Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2930 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4130. Min Range: -8.4130
Max Act: 8.4130. Min Act: -0.1700
Data Index: 257161 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4130. Min Range: -8.4130
Max Act: 8.2255. Min Act: -0.1700
Data Index: 4197858 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4130. Min Range: -8.4130
Max Act: 8.1630. Min Act: -0.1700
Data Index: 2095618 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4130. Min Range: -8.4130
Max Act: 7.9130. Min Act: -0.1700
Data Index: 7839891 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4130. Min Range: -8.4130
Max Act: 8.0380. Min Act: -0.1700
Data Index: 1599839 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4130. Min Range: -8.4130
Max Act: 7.9755. Min Act: -0.1700
Data Index: 2434484 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4130. Min Range: -8.4130
Max Act: 7.8505. Min Act: -0.1700
Data Index: 2313485 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4130. Min Range: -8.4130
Max Act: 7.9130. Min Act: -0.1700
Data Index: 2038123 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4130. Min Range: -8.4130
Max Act: 7.9130. Min Act: -0.1700
Data Index: 2221811 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4130. Min Range: -8.4130
Max Act: 7.9130. Min Act: -0.1700
Data Index: 923219 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4130. Min Range: -8.4130
Max Act: 7.8505. Min Act: -0.1700
Data Index: 5139195 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4130. Min Range: -8.4130
Max Act: 7.8505. Min Act: -0.1700
Data Index: 2455477 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4130. Min Range: -8.4130
Max Act: 7.7880. Min Act: -0.1700
Data Index: 7390508 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4130. Min Range: -8.4130
Max Act: 7.7880. Min Act: -0.1700
Data Index: 1741280 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4130. Min Range: -8.4130
Max Act: 7.7255. Min Act: -0.1700
Data Index: 4638920 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4130. Min Range: -8.4130
Max Act: 7.7255. Min Act: -0.1700
Data Index: 6394980 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4130. Min Range: -8.4130
Max Act: 7.7255. Min Act: -0.1700
Data Index: 2351046 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4130. Min Range: -8.4130
Max Act: 7.6630. Min Act: -0.1700
Data Index: 3196532 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4130. Min Range: -8.4130
Max Act: 7.7255. Min Act: -0.1700
Data Index: 5151580 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4130. Min Range: -8.4130
Max Act: 7.7255. Min Act: -0.1700
Data Index: 1953054 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19