Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 166 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5325. Min Range: -5.5325
Max Act: 5.5325. Min Act: -0.1700
Data Index: 7607702 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5325. Min Range: -5.5325
Max Act: 5.5013. Min Act: -0.1700
Data Index: 8409797 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5325. Min Range: -5.5325
Max Act: 5.4700. Min Act: -0.1700
Data Index: 688012 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5325. Min Range: -5.5325
Max Act: 5.4388. Min Act: -0.1700
Data Index: 3561303 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5325. Min Range: -5.5325
Max Act: 5.4075. Min Act: -0.1700
Data Index: 7059791 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5325. Min Range: -5.5325
Max Act: 5.4075. Min Act: -0.1700
Data Index: 7607707 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5325. Min Range: -5.5325
Max Act: 5.3763. Min Act: -0.1700
Data Index: 8011885 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5325. Min Range: -5.5325
Max Act: 5.3450. Min Act: -0.1700
Data Index: 3772143 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5325. Min Range: -5.5325
Max Act: 5.3450. Min Act: -0.1700
Data Index: 2669946 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5325. Min Range: -5.5325
Max Act: 5.3450. Min Act: -0.1700
Data Index: 2178023 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5325. Min Range: -5.5325
Max Act: 5.2825. Min Act: -0.1700
Data Index: 7579935 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5325. Min Range: -5.5325
Max Act: 5.3138. Min Act: -0.1700
Data Index: 6468476 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5325. Min Range: -5.5325
Max Act: 5.2825. Min Act: -0.1700
Data Index: 4580794 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5325. Min Range: -5.5325
Max Act: 5.2825. Min Act: -0.1700
Data Index: 5802565 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5325. Min Range: -5.5325
Max Act: 5.2825. Min Act: -0.1700
Data Index: 1490045 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5325. Min Range: -5.5325
Max Act: 5.2513. Min Act: -0.1700
Data Index: 4426743 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5325. Min Range: -5.5325
Max Act: 5.2200. Min Act: -0.1700
Data Index: 7607706 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5325. Min Range: -5.5325
Max Act: 5.1575. Min Act: -0.1700
Data Index: 1397407 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5325. Min Range: -5.5325
Max Act: 5.1263. Min Act: -0.1700
Data Index: 4793338 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5325. Min Range: -5.5325
Max Act: 5.1263. Min Act: -0.1700
Data Index: 6014031 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19