Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3862 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5554. Min Range: -3.5554
Max Act: 3.5554. Min Act: -0.1700
Data Index: 5564740 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5554. Min Range: -3.5554
Max Act: 3.4301. Min Act: -0.1700
Data Index: 3307290 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5554. Min Range: -3.5554
Max Act: 3.4301. Min Act: -0.1700
Data Index: 2021036 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5554. Min Range: -3.5554
Max Act: 3.3987. Min Act: -0.1700
Data Index: 7830999 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5554. Min Range: -3.5554
Max Act: 3.3674. Min Act: -0.1700
Data Index: 8776967 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5554. Min Range: -3.5554
Max Act: 3.3360. Min Act: -0.1700
Data Index: 7481514 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5554. Min Range: -3.5554
Max Act: 3.3360. Min Act: -0.1700
Data Index: 6842558 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5554. Min Range: -3.5554
Max Act: 3.3046. Min Act: -0.1700
Data Index: 8095104 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5554. Min Range: -3.5554
Max Act: 3.3046. Min Act: -0.1700
Data Index: 5117310 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5554. Min Range: -3.5554
Max Act: 3.2732. Min Act: -0.1700
Data Index: 48120 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5554. Min Range: -3.5554
Max Act: 3.2732. Min Act: -0.1700
Data Index: 2774319 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5554. Min Range: -3.5554
Max Act: 3.2732. Min Act: -0.1700
Data Index: 1194252 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5554. Min Range: -3.5554
Max Act: 3.2732. Min Act: -0.1700
Data Index: 7178827 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5554. Min Range: -3.5554
Max Act: 3.2732. Min Act: -0.1700
Data Index: 515926 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5554. Min Range: -3.5554
Max Act: 3.3046. Min Act: -0.1700
Data Index: 112111 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5554. Min Range: -3.5554
Max Act: 3.2732. Min Act: -0.1700
Data Index: 6635013 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5554. Min Range: -3.5554
Max Act: 3.2418. Min Act: -0.1700
Data Index: 2456346 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5554. Min Range: -3.5554
Max Act: 3.2418. Min Act: -0.1700
Data Index: 4648590 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5554. Min Range: -3.5554
Max Act: 3.2418. Min Act: -0.1700
Data Index: 1150981 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5554. Min Range: -3.5554
Max Act: 3.2418. Min Act: -0.1700
Data Index: 3603777 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19