Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3309 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5997. Min Range: -5.5997
Max Act: 5.5997. Min Act: -0.1700
Data Index: 8777038 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5997. Min Range: -5.5997
Max Act: 5.5372. Min Act: -0.1700
Data Index: 4385198 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5997. Min Range: -5.5997
Max Act: 5.4435. Min Act: -0.1700
Data Index: 8397267 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5997. Min Range: -5.5997
Max Act: 5.4435. Min Act: -0.1700
Data Index: 3180218 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5997. Min Range: -5.5997
Max Act: 5.4435. Min Act: -0.1700
Data Index: 8344925 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5997. Min Range: -5.5997
Max Act: 5.4122. Min Act: -0.1700
Data Index: 8191832 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5997. Min Range: -5.5997
Max Act: 5.3810. Min Act: -0.1700
Data Index: 2038592 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5997. Min Range: -5.5997
Max Act: 5.3497. Min Act: -0.1700
Data Index: 1968818 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5997. Min Range: -5.5997
Max Act: 5.3810. Min Act: -0.1700
Data Index: 2016059 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5997. Min Range: -5.5997
Max Act: 5.3497. Min Act: -0.1700
Data Index: 5072442 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5997. Min Range: -5.5997
Max Act: 5.3497. Min Act: -0.1700
Data Index: 343330 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5997. Min Range: -5.5997
Max Act: 5.3497. Min Act: -0.1700
Data Index: 2786128 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5997. Min Range: -5.5997
Max Act: 5.3497. Min Act: -0.1700
Data Index: 6110597 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5997. Min Range: -5.5997
Max Act: 5.3497. Min Act: -0.1700
Data Index: 6406310 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5997. Min Range: -5.5997
Max Act: 5.3185. Min Act: -0.1700
Data Index: 1968817 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5997. Min Range: -5.5997
Max Act: 5.2872. Min Act: -0.1700
Data Index: 5889527 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5997. Min Range: -5.5997
Max Act: 5.3185. Min Act: -0.1700
Data Index: 1927312 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5997. Min Range: -5.5997
Max Act: 5.3185. Min Act: -0.1700
Data Index: 7671895 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5997. Min Range: -5.5997
Max Act: 5.3185. Min Act: -0.1700
Data Index: 4071259 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5997. Min Range: -5.5997
Max Act: 5.3185. Min Act: -0.1700
Data Index: 8006392 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19