Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 990 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5133. Min Range: -6.5133
Max Act: 6.5133. Min Act: -0.1700
Data Index: 6323597 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5133. Min Range: -6.5133
Max Act: 5.8883. Min Act: -0.1700
Data Index: 238568 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5133. Min Range: -6.5133
Max Act: 5.9195. Min Act: -0.1700
Data Index: 1561312 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5133. Min Range: -6.5133
Max Act: 5.7945. Min Act: -0.1700
Data Index: 5069510 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5133. Min Range: -6.5133
Max Act: 5.7633. Min Act: -0.1700
Data Index: 4818624 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5133. Min Range: -6.5133
Max Act: 5.7008. Min Act: -0.1700
Data Index: 908064 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5133. Min Range: -6.5133
Max Act: 5.7008. Min Act: -0.1700
Data Index: 3039082 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5133. Min Range: -6.5133
Max Act: 5.7008. Min Act: -0.1700
Data Index: 3221189 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5133. Min Range: -6.5133
Max Act: 5.7320. Min Act: -0.1700
Data Index: 3800367 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5133. Min Range: -6.5133
Max Act: 5.7008. Min Act: -0.1700
Data Index: 2932786 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5133. Min Range: -6.5133
Max Act: 5.7320. Min Act: -0.1700
Data Index: 5843529 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5133. Min Range: -6.5133
Max Act: 5.6383. Min Act: -0.1700
Data Index: 6058422 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5133. Min Range: -6.5133
Max Act: 5.6383. Min Act: -0.1700
Data Index: 4375889 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5133. Min Range: -6.5133
Max Act: 5.6383. Min Act: -0.1700
Data Index: 6710809 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5133. Min Range: -6.5133
Max Act: 5.6383. Min Act: -0.1700
Data Index: 5484554 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5133. Min Range: -6.5133
Max Act: 5.6070. Min Act: -0.1700
Data Index: 6869879 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5133. Min Range: -6.5133
Max Act: 5.5758. Min Act: -0.1700
Data Index: 911747 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5133. Min Range: -6.5133
Max Act: 5.5445. Min Act: -0.1700
Data Index: 3694066 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5133. Min Range: -6.5133
Max Act: 5.5758. Min Act: -0.1700
Data Index: 6640933 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5133. Min Range: -6.5133
Max Act: 5.5445. Min Act: -0.1700
Data Index: 394284 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19