Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3063 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9672. Min Range: -9.9672
Max Act: 9.9672. Min Act: -0.1700
Data Index: 4826442 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9672. Min Range: -9.9672
Max Act: 9.6547. Min Act: -0.1700
Data Index: 1017612 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9672. Min Range: -9.9672
Max Act: 9.5297. Min Act: -0.1700
Data Index: 2783007 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9672. Min Range: -9.9672
Max Act: 9.2172. Min Act: -0.1700
Data Index: 5581390 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9672. Min Range: -9.9672
Max Act: 9.1547. Min Act: -0.1700
Data Index: 1385958 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9672. Min Range: -9.9672
Max Act: 9.0922. Min Act: -0.1700
Data Index: 1726857 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9672. Min Range: -9.9672
Max Act: 9.0922. Min Act: -0.1700
Data Index: 1558151 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9672. Min Range: -9.9672
Max Act: 9.0922. Min Act: -0.1700
Data Index: 7626078 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9672. Min Range: -9.9672
Max Act: 9.0922. Min Act: -0.1700
Data Index: 2362995 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9672. Min Range: -9.9672
Max Act: 9.0297. Min Act: -0.1700
Data Index: 7367836 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9672. Min Range: -9.9672
Max Act: 8.9672. Min Act: -0.1700
Data Index: 4070272 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9672. Min Range: -9.9672
Max Act: 8.9672. Min Act: -0.1700
Data Index: 4400793 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9672. Min Range: -9.9672
Max Act: 8.9047. Min Act: -0.1700
Data Index: 1530593 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9672. Min Range: -9.9672
Max Act: 8.9047. Min Act: -0.1700
Data Index: 8537826 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9672. Min Range: -9.9672
Max Act: 8.8422. Min Act: -0.1700
Data Index: 3527639 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9672. Min Range: -9.9672
Max Act: 8.8422. Min Act: -0.1700
Data Index: 2108205 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9672. Min Range: -9.9672
Max Act: 8.7797. Min Act: -0.1700
Data Index: 5875433 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9672. Min Range: -9.9672
Max Act: 8.7172. Min Act: -0.1700
Data Index: 2456456 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9672. Min Range: -9.9672
Max Act: 8.7172. Min Act: -0.1700
Data Index: 7793703 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9672. Min Range: -9.9672
Max Act: 8.6547. Min Act: -0.1700
Data Index: 6611632 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19