Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1994 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4140. Min Range: -5.4140
Max Act: 5.4140. Min Act: -0.1700
Data Index: 3115335 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4140. Min Range: -5.4140
Max Act: 5.4140. Min Act: -0.1700
Data Index: 5467804 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4140. Min Range: -5.4140
Max Act: 5.2890. Min Act: -0.1700
Data Index: 7655010 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4140. Min Range: -5.4140
Max Act: 5.2265. Min Act: -0.1700
Data Index: 1803058 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4140. Min Range: -5.4140
Max Act: 5.1640. Min Act: -0.1700
Data Index: 1509813 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4140. Min Range: -5.4140
Max Act: 5.1640. Min Act: -0.1700
Data Index: 7093500 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4140. Min Range: -5.4140
Max Act: 5.1640. Min Act: -0.1700
Data Index: 3457278 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4140. Min Range: -5.4140
Max Act: 5.1328. Min Act: -0.1700
Data Index: 6335324 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4140. Min Range: -5.4140
Max Act: 5.1328. Min Act: -0.1700
Data Index: 5815475 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4140. Min Range: -5.4140
Max Act: 5.1328. Min Act: -0.1700
Data Index: 5762358 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4140. Min Range: -5.4140
Max Act: 5.1015. Min Act: -0.1700
Data Index: 4283226 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4140. Min Range: -5.4140
Max Act: 5.1015. Min Act: -0.1700
Data Index: 7944443 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4140. Min Range: -5.4140
Max Act: 5.1328. Min Act: -0.1700
Data Index: 3627056 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4140. Min Range: -5.4140
Max Act: 5.0703. Min Act: -0.1700
Data Index: 2745685 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4140. Min Range: -5.4140
Max Act: 5.0703. Min Act: -0.1700
Data Index: 7448496 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4140. Min Range: -5.4140
Max Act: 5.0703. Min Act: -0.1700
Data Index: 3085653 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4140. Min Range: -5.4140
Max Act: 5.0390. Min Act: -0.1700
Data Index: 3779182 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4140. Min Range: -5.4140
Max Act: 5.0703. Min Act: -0.1700
Data Index: 5191311 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4140. Min Range: -5.4140
Max Act: 5.0078. Min Act: -0.1700
Data Index: 7241414 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4140. Min Range: -5.4140
Max Act: 5.0078. Min Act: -0.1700
Data Index: 7643003 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19