Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2346. Min Range: -5.2346
Max Act: 5.2346. Min Act: -0.1700
Data Index: 4711372 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2346. Min Range: -5.2346
Max Act: 5.1409. Min Act: -0.1699
Data Index: 6393049 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2346. Min Range: -5.2346
Max Act: 5.0784. Min Act: -0.1700
Data Index: 5903390 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2346. Min Range: -5.2346
Max Act: 5.0159. Min Act: -0.1700
Data Index: 6291841 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2346. Min Range: -5.2346
Max Act: 5.0471. Min Act: -0.1700
Data Index: 2775176 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2346. Min Range: -5.2346
Max Act: 5.0471. Min Act: -0.1700
Data Index: 4458322 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2346. Min Range: -5.2346
Max Act: 5.0471. Min Act: -0.1700
Data Index: 87229 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2346. Min Range: -5.2346
Max Act: 5.0471. Min Act: -0.1698
Data Index: 4438673 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2346. Min Range: -5.2346
Max Act: 5.0471. Min Act: -0.1700
Data Index: 7092707 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2346. Min Range: -5.2346
Max Act: 5.0159. Min Act: -0.1700
Data Index: 2124928 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2346. Min Range: -5.2346
Max Act: 5.0159. Min Act: -0.1700
Data Index: 8404380 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2346. Min Range: -5.2346
Max Act: 5.0159. Min Act: -0.1700
Data Index: 1122746 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2346. Min Range: -5.2346
Max Act: 4.9846. Min Act: -0.1700
Data Index: 3831998 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2346. Min Range: -5.2346
Max Act: 5.0159. Min Act: -0.1700
Data Index: 6686458 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2346. Min Range: -5.2346
Max Act: 4.9846. Min Act: -0.1700
Data Index: 5452082 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2346. Min Range: -5.2346
Max Act: 4.9846. Min Act: -0.1700
Data Index: 3217805 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2346. Min Range: -5.2346
Max Act: 4.9846. Min Act: -0.1700
Data Index: 5757616 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2346. Min Range: -5.2346
Max Act: 4.9846. Min Act: -0.1700
Data Index: 2332028 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2346. Min Range: -5.2346
Max Act: 4.9846. Min Act: -0.1700
Data Index: 6074860 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2346. Min Range: -5.2346
Max Act: 4.9846. Min Act: -0.1700
Data Index: 2847090 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19