Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3084 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3910. Min Range: -8.3910
Max Act: 8.3910. Min Act: -0.1700
Data Index: 1244299 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3910. Min Range: -8.3910
Max Act: 8.2660. Min Act: -0.1700
Data Index: 2023964 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3910. Min Range: -8.3910
Max Act: 8.2660. Min Act: -0.1700
Data Index: 7359363 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3910. Min Range: -8.3910
Max Act: 8.3285. Min Act: -0.1700
Data Index: 6819892 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3910. Min Range: -8.3910
Max Act: 8.2035. Min Act: -0.1700
Data Index: 7061415 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3910. Min Range: -8.3910
Max Act: 8.0785. Min Act: -0.1700
Data Index: 5567037 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3910. Min Range: -8.3910
Max Act: 8.0785. Min Act: -0.1700
Data Index: 6879854 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3910. Min Range: -8.3910
Max Act: 8.0785. Min Act: -0.1700
Data Index: 2022544 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3910. Min Range: -8.3910
Max Act: 8.0160. Min Act: -0.1700
Data Index: 5322059 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3910. Min Range: -8.3910
Max Act: 7.9534. Min Act: -0.1700
Data Index: 8635959 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3910. Min Range: -8.3910
Max Act: 7.9534. Min Act: -0.1700
Data Index: 8751661 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3910. Min Range: -8.3910
Max Act: 7.8909. Min Act: -0.1700
Data Index: 549460 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3910. Min Range: -8.3910
Max Act: 7.8909. Min Act: -0.1700
Data Index: 5877303 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3910. Min Range: -8.3910
Max Act: 7.8909. Min Act: -0.1700
Data Index: 122006 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3910. Min Range: -8.3910
Max Act: 7.7659. Min Act: -0.1700
Data Index: 5270548 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3910. Min Range: -8.3910
Max Act: 7.7659. Min Act: -0.1700
Data Index: 6360278 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3910. Min Range: -8.3910
Max Act: 7.7659. Min Act: -0.1700
Data Index: 3993099 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3910. Min Range: -8.3910
Max Act: 7.8284. Min Act: -0.1700
Data Index: 6817575 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3910. Min Range: -8.3910
Max Act: 7.6409. Min Act: -0.1700
Data Index: 301503 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3910. Min Range: -8.3910
Max Act: 7.6409. Min Act: -0.1700
Data Index: 1144764 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19