Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3177 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7145. Min Range: -2.7145
Max Act: 2.7145. Min Act: -0.1700
Data Index: 5296023 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7145. Min Range: -2.7145
Max Act: 2.6665. Min Act: -0.1700
Data Index: 273929 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7145. Min Range: -2.7145
Max Act: 2.6344. Min Act: -0.1700
Data Index: 1900237 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7145. Min Range: -2.7145
Max Act: 2.6505. Min Act: -0.1700
Data Index: 1684925 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7145. Min Range: -2.7145
Max Act: 2.6183. Min Act: -0.1700
Data Index: 7776221 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7145. Min Range: -2.7145
Max Act: 2.6183. Min Act: -0.1700
Data Index: 6995881 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7145. Min Range: -2.7145
Max Act: 2.6023. Min Act: -0.1700
Data Index: 5885114 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7145. Min Range: -2.7145
Max Act: 2.5862. Min Act: -0.1700
Data Index: 1483402 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7145. Min Range: -2.7145
Max Act: 2.5862. Min Act: -0.1700
Data Index: 7126527 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7145. Min Range: -2.7145
Max Act: 2.5539. Min Act: -0.1700
Data Index: 2766822 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7145. Min Range: -2.7145
Max Act: 2.5700. Min Act: -0.1700
Data Index: 1930931 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7145. Min Range: -2.7145
Max Act: 2.5539. Min Act: -0.1700
Data Index: 2268213 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7145. Min Range: -2.7145
Max Act: 2.5700. Min Act: -0.1700
Data Index: 1754189 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7145. Min Range: -2.7145
Max Act: 2.5539. Min Act: -0.1700
Data Index: 8324791 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7145. Min Range: -2.7145
Max Act: 2.5539. Min Act: -0.1700
Data Index: 2595180 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7145. Min Range: -2.7145
Max Act: 2.5539. Min Act: -0.1700
Data Index: 4554044 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7145. Min Range: -2.7145
Max Act: 2.5378. Min Act: -0.1700
Data Index: 6649378 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7145. Min Range: -2.7145
Max Act: 2.5539. Min Act: -0.1700
Data Index: 1009588 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7145. Min Range: -2.7145
Max Act: 2.5378. Min Act: -0.1700
Data Index: 1631585 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7145. Min Range: -2.7145
Max Act: 2.5539. Min Act: -0.1700
Data Index: 8620561 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19