Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2757 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6119. Min Range: -5.6119
Max Act: 5.6119. Min Act: -0.1700
Data Index: 4346673 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6119. Min Range: -5.6119
Max Act: 5.4869. Min Act: -0.1700
Data Index: 3204725 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6119. Min Range: -5.6119
Max Act: 5.4244. Min Act: -0.1700
Data Index: 311954 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6119. Min Range: -5.6119
Max Act: 5.4556. Min Act: -0.1700
Data Index: 7395286 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6119. Min Range: -5.6119
Max Act: 5.4244. Min Act: -0.1700
Data Index: 4231896 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6119. Min Range: -5.6119
Max Act: 5.3619. Min Act: -0.1700
Data Index: 5051983 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6119. Min Range: -5.6119
Max Act: 5.2994. Min Act: -0.1700
Data Index: 4464009 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6119. Min Range: -5.6119
Max Act: 5.2994. Min Act: -0.1700
Data Index: 5762551 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6119. Min Range: -5.6119
Max Act: 5.2681. Min Act: -0.1700
Data Index: 7723358 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6119. Min Range: -5.6119
Max Act: 5.2369. Min Act: -0.1700
Data Index: 120620 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6119. Min Range: -5.6119
Max Act: 5.2056. Min Act: -0.1700
Data Index: 8399320 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6119. Min Range: -5.6119
Max Act: 5.2056. Min Act: -0.1700
Data Index: 4355148 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6119. Min Range: -5.6119
Max Act: 5.1744. Min Act: -0.1700
Data Index: 153703 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6119. Min Range: -5.6119
Max Act: 5.2056. Min Act: -0.1700
Data Index: 7168532 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6119. Min Range: -5.6119
Max Act: 5.1431. Min Act: -0.1700
Data Index: 6584563 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6119. Min Range: -5.6119
Max Act: 5.1431. Min Act: -0.1700
Data Index: 1774531 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6119. Min Range: -5.6119
Max Act: 5.1119. Min Act: -0.1700
Data Index: 2007571 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6119. Min Range: -5.6119
Max Act: 5.0806. Min Act: -0.1700
Data Index: 3769006 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6119. Min Range: -5.6119
Max Act: 5.0806. Min Act: -0.1700
Data Index: 1488437 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6119. Min Range: -5.6119
Max Act: 5.0806. Min Act: -0.1700
Data Index: 6404701 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19