Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3464 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4681. Min Range: -5.4681
Max Act: 5.4681. Min Act: -0.1700
Data Index: 8771469 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4681. Min Range: -5.4681
Max Act: 5.3431. Min Act: -0.1700
Data Index: 4865513 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4681. Min Range: -5.4681
Max Act: 5.2806. Min Act: -0.1700
Data Index: 5679667 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4681. Min Range: -5.4681
Max Act: 5.1243. Min Act: -0.1700
Data Index: 2771701 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4681. Min Range: -5.4681
Max Act: 5.0931. Min Act: -0.1700
Data Index: 2108977 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4681. Min Range: -5.4681
Max Act: 5.0306. Min Act: -0.1700
Data Index: 737834 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4681. Min Range: -5.4681
Max Act: 4.9993. Min Act: -0.1700
Data Index: 5874144 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4681. Min Range: -5.4681
Max Act: 4.9993. Min Act: -0.1700
Data Index: 1337167 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4681. Min Range: -5.4681
Max Act: 4.9993. Min Act: -0.1700
Data Index: 842469 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4681. Min Range: -5.4681
Max Act: 4.9681. Min Act: -0.1700
Data Index: 165149 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4681. Min Range: -5.4681
Max Act: 4.9681. Min Act: -0.1700
Data Index: 7710882 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4681. Min Range: -5.4681
Max Act: 4.9681. Min Act: -0.1700
Data Index: 1463604 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4681. Min Range: -5.4681
Max Act: 4.9368. Min Act: -0.1700
Data Index: 2802464 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4681. Min Range: -5.4681
Max Act: 4.9368. Min Act: -0.1700
Data Index: 6518195 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4681. Min Range: -5.4681
Max Act: 4.9368. Min Act: -0.1700
Data Index: 214666 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4681. Min Range: -5.4681
Max Act: 4.9056. Min Act: -0.1700
Data Index: 842470 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4681. Min Range: -5.4681
Max Act: 4.9056. Min Act: -0.1700
Data Index: 7267077 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4681. Min Range: -5.4681
Max Act: 4.9056. Min Act: -0.1700
Data Index: 1928100 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4681. Min Range: -5.4681
Max Act: 4.9056. Min Act: -0.1700
Data Index: 4146977 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4681. Min Range: -5.4681
Max Act: 4.9056. Min Act: -0.1700
Data Index: 2177591 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19