Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5698 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3802. Min Range: -3.3802
Max Act: 3.3802. Min Act: -0.1700
Data Index: 8503062 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3802. Min Range: -3.3802
Max Act: 3.3332. Min Act: -0.1700
Data Index: 6556441 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3802. Min Range: -3.3802
Max Act: 3.2547. Min Act: -0.1700
Data Index: 2962796 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3802. Min Range: -3.3802
Max Act: 3.2389. Min Act: -0.1700
Data Index: 3256082 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3802. Min Range: -3.3802
Max Act: 3.2232. Min Act: -0.1700
Data Index: 5987829 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3802. Min Range: -3.3802
Max Act: 3.2075. Min Act: -0.1700
Data Index: 3249534 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3802. Min Range: -3.3802
Max Act: 3.2075. Min Act: -0.1700
Data Index: 3835554 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3802. Min Range: -3.3802
Max Act: 3.1918. Min Act: -0.1700
Data Index: 8033496 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3802. Min Range: -3.3802
Max Act: 3.1761. Min Act: -0.1700
Data Index: 8503061 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3802. Min Range: -3.3802
Max Act: 3.1603. Min Act: -0.1700
Data Index: 7755891 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3802. Min Range: -3.3802
Max Act: 3.1603. Min Act: -0.1700
Data Index: 8503067 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3802. Min Range: -3.3802
Max Act: 3.1446. Min Act: -0.1700
Data Index: 2171023 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3802. Min Range: -3.3802
Max Act: 3.1446. Min Act: -0.1700
Data Index: 265626 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3802. Min Range: -3.3802
Max Act: 3.1288. Min Act: -0.1700
Data Index: 8503066 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3802. Min Range: -3.3802
Max Act: 3.1131. Min Act: -0.1700
Data Index: 2226263 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3802. Min Range: -3.3802
Max Act: 3.1131. Min Act: -0.1700
Data Index: 3124578 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3802. Min Range: -3.3802
Max Act: 3.0816. Min Act: -0.1700
Data Index: 179625 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3802. Min Range: -3.3802
Max Act: 3.0816. Min Act: -0.1700
Data Index: 3961075 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3802. Min Range: -3.3802
Max Act: 3.0816. Min Act: -0.1700
Data Index: 8397117 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3802. Min Range: -3.3802
Max Act: 3.0973. Min Act: -0.1700
Data Index: 8503060 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19