Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1630 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.8337. Min Act: -0.1700
Data Index: 1908670 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.8025. Min Act: -0.1700
Data Index: 671510 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.7400. Min Act: -0.1700
Data Index: 8061049 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.7087. Min Act: -0.1700
Data Index: 399315 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.7400. Min Act: -0.1700
Data Index: 1047733 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.7400. Min Act: -0.1700
Data Index: 7396509 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.6775. Min Act: -0.1700
Data Index: 2343200 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.6462. Min Act: -0.1700
Data Index: 5729099 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.6775. Min Act: -0.1700
Data Index: 3735451 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.6462. Min Act: -0.1700
Data Index: 7703849 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.6462. Min Act: -0.1700
Data Index: 4676285 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.6150. Min Act: -0.1700
Data Index: 7123311 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.6150. Min Act: -0.1700
Data Index: 4015020 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.6150. Min Act: -0.1700
Data Index: 3243466 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.6150. Min Act: -0.1700
Data Index: 2269699 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.5837. Min Act: -0.1700
Data Index: 2265061 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.6150. Min Act: -0.1700
Data Index: 4455137 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.5525. Min Act: -0.1700
Data Index: 8465864 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.5525. Min Act: -0.1700
Data Index: 6687291 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.5837. Min Act: -0.1700
Data Index: 699017 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19