Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1743 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6280. Min Range: -6.6280
Max Act: 6.6280. Min Act: -0.1700
Data Index: 2113822 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6280. Min Range: -6.6280
Max Act: 6.5968. Min Act: -0.1700
Data Index: 6674704 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6280. Min Range: -6.6280
Max Act: 6.3155. Min Act: -0.1700
Data Index: 6838737 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6280. Min Range: -6.6280
Max Act: 6.2843. Min Act: -0.1700
Data Index: 522109 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6280. Min Range: -6.6280
Max Act: 6.2843. Min Act: -0.1700
Data Index: 6429103 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6280. Min Range: -6.6280
Max Act: 6.2218. Min Act: -0.1700
Data Index: 8471723 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6280. Min Range: -6.6280
Max Act: 6.1905. Min Act: -0.1700
Data Index: 6006838 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6280. Min Range: -6.6280
Max Act: 6.1593. Min Act: -0.1700
Data Index: 4041225 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6280. Min Range: -6.6280
Max Act: 6.1280. Min Act: -0.1700
Data Index: 2882368 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6280. Min Range: -6.6280
Max Act: 6.1593. Min Act: -0.1700
Data Index: 713863 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6280. Min Range: -6.6280
Max Act: 6.1280. Min Act: -0.1700
Data Index: 708530 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6280. Min Range: -6.6280
Max Act: 6.1280. Min Act: -0.1700
Data Index: 7624372 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6280. Min Range: -6.6280
Max Act: 6.0968. Min Act: -0.1700
Data Index: 4009417 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6280. Min Range: -6.6280
Max Act: 6.0968. Min Act: -0.1700
Data Index: 8469282 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6280. Min Range: -6.6280
Max Act: 6.0968. Min Act: -0.1700
Data Index: 770600 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6280. Min Range: -6.6280
Max Act: 6.0968. Min Act: -0.1700
Data Index: 7915863 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6280. Min Range: -6.6280
Max Act: 6.0968. Min Act: -0.1700
Data Index: 5701193 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6280. Min Range: -6.6280
Max Act: 6.0968. Min Act: -0.1700
Data Index: 8022299 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6280. Min Range: -6.6280
Max Act: 6.0968. Min Act: -0.1700
Data Index: 7317259 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6280. Min Range: -6.6280
Max Act: 6.0655. Min Act: -0.1700
Data Index: 491730 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19