Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3358 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4330. Min Range: -5.4330
Max Act: 5.4330. Min Act: -0.1700
Data Index: 2775131 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4330. Min Range: -5.4330
Max Act: 5.3705. Min Act: -0.1700
Data Index: 2116619 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4330. Min Range: -5.4330
Max Act: 5.3705. Min Act: -0.1700
Data Index: 3520271 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4330. Min Range: -5.4330
Max Act: 5.3393. Min Act: -0.1700
Data Index: 2332971 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4330. Min Range: -5.4330
Max Act: 5.3080. Min Act: -0.1700
Data Index: 575019 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4330. Min Range: -5.4330
Max Act: 5.2768. Min Act: -0.1700
Data Index: 7475209 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4330. Min Range: -5.4330
Max Act: 5.3080. Min Act: -0.1700
Data Index: 5060045 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4330. Min Range: -5.4330
Max Act: 5.2768. Min Act: -0.1700
Data Index: 8731621 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4330. Min Range: -5.4330
Max Act: 5.2455. Min Act: -0.1700
Data Index: 2777771 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4330. Min Range: -5.4330
Max Act: 5.2455. Min Act: -0.1700
Data Index: 6923417 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4330. Min Range: -5.4330
Max Act: 5.2455. Min Act: -0.1700
Data Index: 1327200 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4330. Min Range: -5.4330
Max Act: 5.2455. Min Act: -0.1700
Data Index: 2734792 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4330. Min Range: -5.4330
Max Act: 5.2455. Min Act: -0.1700
Data Index: 3532266 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4330. Min Range: -5.4330
Max Act: 5.2455. Min Act: -0.1700
Data Index: 8630680 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4330. Min Range: -5.4330
Max Act: 5.2455. Min Act: -0.1700
Data Index: 8588775 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4330. Min Range: -5.4330
Max Act: 5.2768. Min Act: -0.1700
Data Index: 2814561 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4330. Min Range: -5.4330
Max Act: 5.2143. Min Act: -0.1700
Data Index: 632963 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4330. Min Range: -5.4330
Max Act: 5.2143. Min Act: -0.1700
Data Index: 6793915 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4330. Min Range: -5.4330
Max Act: 5.2143. Min Act: -0.1700
Data Index: 3758907 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4330. Min Range: -5.4330
Max Act: 5.2143. Min Act: -0.1700
Data Index: 1342637 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19