Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2268 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3805. Min Range: -1.3805
Max Act: 1.3805. Min Act: -0.1700
Data Index: 100682 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3805. Min Range: -1.3805
Max Act: 1.3629. Min Act: -0.1700
Data Index: 729920 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3805. Min Range: -1.3805
Max Act: 1.3452. Min Act: -0.1700
Data Index: 1004923 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3805. Min Range: -1.3805
Max Act: 1.3276. Min Act: -0.1700
Data Index: 2758673 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3805. Min Range: -1.3805
Max Act: 1.3276. Min Act: -0.1700
Data Index: 3899338 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3805. Min Range: -1.3805
Max Act: 1.3276. Min Act: -0.1700
Data Index: 1017758 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3805. Min Range: -1.3805
Max Act: 1.2747. Min Act: -0.1700
Data Index: 7524223 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3805. Min Range: -1.3805
Max Act: 1.2747. Min Act: -0.1700
Data Index: 7231696 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3805. Min Range: -1.3805
Max Act: 1.2747. Min Act: -0.1700
Data Index: 7438169 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3805. Min Range: -1.3805
Max Act: 1.2747. Min Act: -0.1700
Data Index: 7524796 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3805. Min Range: -1.3805
Max Act: 1.2923. Min Act: -0.1700
Data Index: 8739448 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3805. Min Range: -1.3805
Max Act: 1.2570. Min Act: -0.1699
Data Index: 2546522 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3805. Min Range: -1.3805
Max Act: 1.2570. Min Act: -0.1700
Data Index: 7056154 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3805. Min Range: -1.3805
Max Act: 1.2747. Min Act: -0.1700
Data Index: 7001857 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3805. Min Range: -1.3805
Max Act: 1.2570. Min Act: -0.1700
Data Index: 3293472 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3805. Min Range: -1.3805
Max Act: 1.2394. Min Act: -0.1700
Data Index: 2131031 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3805. Min Range: -1.3805
Max Act: 1.2394. Min Act: -0.1700
Data Index: 6624484 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3805. Min Range: -1.3805
Max Act: 1.2394. Min Act: -0.1700
Data Index: 6465046 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3805. Min Range: -1.3805
Max Act: 1.2394. Min Act: -0.1700
Data Index: 1050516 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3805. Min Range: -1.3805
Max Act: 1.2394. Min Act: -0.1700
Data Index: 4719687 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19