Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 54 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1369. Min Range: -5.1369
Max Act: 5.1369. Min Act: -0.1700
Data Index: 132664 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1369. Min Range: -5.1369
Max Act: 5.0119. Min Act: -0.1700
Data Index: 106104 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1369. Min Range: -5.1369
Max Act: 4.9807. Min Act: -0.1700
Data Index: 855311 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1369. Min Range: -5.1369
Max Act: 4.8869. Min Act: -0.1700
Data Index: 2984315 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1369. Min Range: -5.1369
Max Act: 4.8244. Min Act: -0.1700
Data Index: 7582039 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1369. Min Range: -5.1369
Max Act: 4.7932. Min Act: -0.1700
Data Index: 2789151 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1369. Min Range: -5.1369
Max Act: 4.7932. Min Act: -0.1700
Data Index: 8141879 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1369. Min Range: -5.1369
Max Act: 4.7619. Min Act: -0.1700
Data Index: 7125643 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1369. Min Range: -5.1369
Max Act: 4.7619. Min Act: -0.1700
Data Index: 1571887 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1369. Min Range: -5.1369
Max Act: 4.7307. Min Act: -0.1700
Data Index: 5528757 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1369. Min Range: -5.1369
Max Act: 4.7307. Min Act: -0.1700
Data Index: 4736080 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1369. Min Range: -5.1369
Max Act: 4.6994. Min Act: -0.1700
Data Index: 6781776 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1369. Min Range: -5.1369
Max Act: 4.6994. Min Act: -0.1700
Data Index: 3946527 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1369. Min Range: -5.1369
Max Act: 4.6057. Min Act: -0.1700
Data Index: 3627666 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1369. Min Range: -5.1369
Max Act: 4.6057. Min Act: -0.1700
Data Index: 339097 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1369. Min Range: -5.1369
Max Act: 4.6057. Min Act: -0.1700
Data Index: 6301200 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1369. Min Range: -5.1369
Max Act: 4.6057. Min Act: -0.1700
Data Index: 4167569 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1369. Min Range: -5.1369
Max Act: 4.6057. Min Act: -0.1700
Data Index: 7131770 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1369. Min Range: -5.1369
Max Act: 4.5744. Min Act: -0.1700
Data Index: 336754 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1369. Min Range: -5.1369
Max Act: 4.5744. Min Act: -0.1700
Data Index: 6388224 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19