Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 815 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.0159. Min Range: -6.0159
Max Act: 6.0159. Min Act: -0.1700
Data Index: 7261424 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0159. Min Range: -6.0159
Max Act: 5.9534. Min Act: -0.1700
Data Index: 3067599 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0159. Min Range: -6.0159
Max Act: 5.8909. Min Act: -0.1700
Data Index: 5022420 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0159. Min Range: -6.0159
Max Act: 5.7972. Min Act: -0.1700
Data Index: 5623014 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0159. Min Range: -6.0159
Max Act: 5.7347. Min Act: -0.1700
Data Index: 2554372 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0159. Min Range: -6.0159
Max Act: 5.7034. Min Act: -0.1700
Data Index: 3190115 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0159. Min Range: -6.0159
Max Act: 5.7034. Min Act: -0.1700
Data Index: 8373618 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0159. Min Range: -6.0159
Max Act: 5.6097. Min Act: -0.1700
Data Index: 807653 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0159. Min Range: -6.0159
Max Act: 5.6722. Min Act: -0.1700
Data Index: 4760834 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0159. Min Range: -6.0159
Max Act: 5.6722. Min Act: -0.1700
Data Index: 6853846 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0159. Min Range: -6.0159
Max Act: 5.6722. Min Act: -0.1700
Data Index: 5107958 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0159. Min Range: -6.0159
Max Act: 5.6097. Min Act: -0.1700
Data Index: 3330802 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0159. Min Range: -6.0159
Max Act: 5.6097. Min Act: -0.1700
Data Index: 3706624 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0159. Min Range: -6.0159
Max Act: 5.6722. Min Act: -0.1700
Data Index: 6540016 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0159. Min Range: -6.0159
Max Act: 5.6722. Min Act: -0.1700
Data Index: 166282 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0159. Min Range: -6.0159
Max Act: 5.6097. Min Act: -0.1700
Data Index: 2095751 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0159. Min Range: -6.0159
Max Act: 5.6097. Min Act: -0.1700
Data Index: 4040029 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0159. Min Range: -6.0159
Max Act: 5.5784. Min Act: -0.1700
Data Index: 7012471 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0159. Min Range: -6.0159
Max Act: 5.5784. Min Act: -0.1700
Data Index: 6941683 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0159. Min Range: -6.0159
Max Act: 5.6097. Min Act: -0.1700
Data Index: 5263670 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19