Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 213 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2206. Min Range: -5.2206
Max Act: 5.2206. Min Act: -0.1700
Data Index: 1667137 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2206. Min Range: -5.2206
Max Act: 5.2206. Min Act: -0.1700
Data Index: 5732830 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2206. Min Range: -5.2206
Max Act: 5.0643. Min Act: -0.1700
Data Index: 3865809 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2206. Min Range: -5.2206
Max Act: 5.0643. Min Act: -0.1700
Data Index: 4776156 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2206. Min Range: -5.2206
Max Act: 5.0018. Min Act: -0.1700
Data Index: 3992712 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2206. Min Range: -5.2206
Max Act: 5.0331. Min Act: -0.1700
Data Index: 2794615 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2206. Min Range: -5.2206
Max Act: 5.0331. Min Act: -0.1700
Data Index: 8423062 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2206. Min Range: -5.2206
Max Act: 5.0018. Min Act: -0.1700
Data Index: 2968049 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2206. Min Range: -5.2206
Max Act: 5.0018. Min Act: -0.1700
Data Index: 1440548 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2206. Min Range: -5.2206
Max Act: 5.0018. Min Act: -0.1700
Data Index: 7661567 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2206. Min Range: -5.2206
Max Act: 5.0018. Min Act: -0.1700
Data Index: 176821 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2206. Min Range: -5.2206
Max Act: 4.9706. Min Act: -0.1700
Data Index: 2879773 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2206. Min Range: -5.2206
Max Act: 4.9706. Min Act: -0.1700
Data Index: 8233841 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2206. Min Range: -5.2206
Max Act: 4.9706. Min Act: -0.1700
Data Index: 8214788 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2206. Min Range: -5.2206
Max Act: 4.9081. Min Act: -0.1700
Data Index: 3553114 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2206. Min Range: -5.2206
Max Act: 4.9706. Min Act: -0.1700
Data Index: 62936 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2206. Min Range: -5.2206
Max Act: 4.9081. Min Act: -0.1700
Data Index: 5345885 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2206. Min Range: -5.2206
Max Act: 4.9081. Min Act: -0.1700
Data Index: 4984325 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2206. Min Range: -5.2206
Max Act: 4.9393. Min Act: -0.1700
Data Index: 1393533 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2206. Min Range: -5.2206
Max Act: 4.9081. Min Act: -0.1700
Data Index: 7023985 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19