Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1555 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8508. Min Range: -6.8508
Max Act: 6.8508. Min Act: -0.1700
Data Index: 5892870 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8508. Min Range: -6.8508
Max Act: 6.7570. Min Act: -0.1700
Data Index: 7135906 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8508. Min Range: -6.8508
Max Act: 6.6945. Min Act: -0.1700
Data Index: 2407346 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8508. Min Range: -6.8508
Max Act: 6.6945. Min Act: -0.1700
Data Index: 7134864 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8508. Min Range: -6.8508
Max Act: 6.6945. Min Act: -0.1700
Data Index: 5268071 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8508. Min Range: -6.8508
Max Act: 6.6320. Min Act: -0.1700
Data Index: 4000391 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8508. Min Range: -6.8508
Max Act: 6.6008. Min Act: -0.1700
Data Index: 4910051 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8508. Min Range: -6.8508
Max Act: 6.5383. Min Act: -0.1700
Data Index: 8574282 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8508. Min Range: -6.8508
Max Act: 6.5695. Min Act: -0.1700
Data Index: 4132035 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8508. Min Range: -6.8508
Max Act: 6.5383. Min Act: -0.1700
Data Index: 416624 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8508. Min Range: -6.8508
Max Act: 6.5383. Min Act: -0.1700
Data Index: 4347886 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8508. Min Range: -6.8508
Max Act: 6.5070. Min Act: -0.1700
Data Index: 1840349 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8508. Min Range: -6.8508
Max Act: 6.5383. Min Act: -0.1700
Data Index: 1814562 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8508. Min Range: -6.8508
Max Act: 6.5070. Min Act: -0.1700
Data Index: 461622 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8508. Min Range: -6.8508
Max Act: 6.4758. Min Act: -0.1700
Data Index: 7715007 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8508. Min Range: -6.8508
Max Act: 6.4445. Min Act: -0.1700
Data Index: 7010436 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8508. Min Range: -6.8508
Max Act: 6.4133. Min Act: -0.1700
Data Index: 7234898 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8508. Min Range: -6.8508
Max Act: 6.4133. Min Act: -0.1700
Data Index: 2502696 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8508. Min Range: -6.8508
Max Act: 6.3820. Min Act: -0.1700
Data Index: 6837325 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8508. Min Range: -6.8508
Max Act: 6.3820. Min Act: -0.1700
Data Index: 4109700 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19