Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4395. Min Range: -6.4395
Max Act: 6.4395. Min Act: -0.1700
Data Index: 7730209 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4395. Min Range: -6.4395
Max Act: 6.4082. Min Act: -0.1700
Data Index: 6425484 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4395. Min Range: -6.4395
Max Act: 6.3457. Min Act: -0.1700
Data Index: 3841559 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4395. Min Range: -6.4395
Max Act: 6.3457. Min Act: -0.1700
Data Index: 7926487 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4395. Min Range: -6.4395
Max Act: 6.3145. Min Act: -0.1700
Data Index: 1543004 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4395. Min Range: -6.4395
Max Act: 6.3145. Min Act: -0.1700
Data Index: 4373521 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4395. Min Range: -6.4395
Max Act: 6.2832. Min Act: -0.1700
Data Index: 2162548 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4395. Min Range: -6.4395
Max Act: 6.2832. Min Act: -0.1700
Data Index: 8004149 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4395. Min Range: -6.4395
Max Act: 6.3145. Min Act: -0.1700
Data Index: 97996 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4395. Min Range: -6.4395
Max Act: 6.2520. Min Act: -0.1700
Data Index: 3124332 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4395. Min Range: -6.4395
Max Act: 6.3145. Min Act: -0.1700
Data Index: 1286103 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4395. Min Range: -6.4395
Max Act: 6.2207. Min Act: -0.1700
Data Index: 3271635 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4395. Min Range: -6.4395
Max Act: 6.2520. Min Act: -0.1700
Data Index: 6521315 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4395. Min Range: -6.4395
Max Act: 6.1895. Min Act: -0.1700
Data Index: 1924248 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4395. Min Range: -6.4395
Max Act: 6.2207. Min Act: -0.1700
Data Index: 4481485 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4395. Min Range: -6.4395
Max Act: 6.1582. Min Act: -0.1700
Data Index: 3256205 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4395. Min Range: -6.4395
Max Act: 6.1582. Min Act: -0.1700
Data Index: 6833212 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4395. Min Range: -6.4395
Max Act: 6.1582. Min Act: -0.1700
Data Index: 3436678 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4395. Min Range: -6.4395
Max Act: 6.1895. Min Act: -0.1700
Data Index: 6039404 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4395. Min Range: -6.4395
Max Act: 6.1270. Min Act: -0.1700
Data Index: 2573482 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19