Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3741 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3140. Min Range: -3.3140
Max Act: 3.3140. Min Act: -0.1700
Data Index: 8101574 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3140. Min Range: -3.3140
Max Act: 3.2512. Min Act: -0.1700
Data Index: 3641257 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3140. Min Range: -3.3140
Max Act: 3.2197. Min Act: -0.1700
Data Index: 3088805 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3140. Min Range: -3.3140
Max Act: 3.2040. Min Act: -0.1700
Data Index: 6135223 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3140. Min Range: -3.3140
Max Act: 3.0781. Min Act: -0.1700
Data Index: 6613099 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3140. Min Range: -3.3140
Max Act: 3.0149. Min Act: -0.1700
Data Index: 1932100 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3140. Min Range: -3.3140
Max Act: 2.9675. Min Act: -0.1700
Data Index: 4132697 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3140. Min Range: -3.3140
Max Act: 2.9675. Min Act: -0.1700
Data Index: 1183013 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3140. Min Range: -3.3140
Max Act: 2.9041. Min Act: -0.1700
Data Index: 5884448 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3140. Min Range: -3.3140
Max Act: 2.9041. Min Act: -0.1700
Data Index: 5790113 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3140. Min Range: -3.3140
Max Act: 2.9041. Min Act: -0.1700
Data Index: 5556141 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3140. Min Range: -3.3140
Max Act: 2.9041. Min Act: -0.1700
Data Index: 1950428 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3140. Min Range: -3.3140
Max Act: 2.8406. Min Act: -0.1700
Data Index: 6879168 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3140. Min Range: -3.3140
Max Act: 2.8406. Min Act: -0.1700
Data Index: 3811709 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3140. Min Range: -3.3140
Max Act: 2.8565. Min Act: -0.1700
Data Index: 8247472 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3140. Min Range: -3.3140
Max Act: 2.8247. Min Act: -0.1700
Data Index: 1010918 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3140. Min Range: -3.3140
Max Act: 2.8247. Min Act: -0.1700
Data Index: 3874707 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3140. Min Range: -3.3140
Max Act: 2.8247. Min Act: -0.1700
Data Index: 3880210 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3140. Min Range: -3.3140
Max Act: 2.8247. Min Act: -0.1700
Data Index: 4746584 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3140. Min Range: -3.3140
Max Act: 2.8247. Min Act: -0.1700
Data Index: 5616291 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19