Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5965 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8205. Min Range: -5.8205
Max Act: 5.8205. Min Act: -0.1700
Data Index: 5184882 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8205. Min Range: -5.8205
Max Act: 5.5393. Min Act: -0.1700
Data Index: 3834275 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8205. Min Range: -5.8205
Max Act: 5.4768. Min Act: -0.1700
Data Index: 811785 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8205. Min Range: -5.8205
Max Act: 5.4768. Min Act: -0.1700
Data Index: 5969786 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8205. Min Range: -5.8205
Max Act: 5.4455. Min Act: -0.1700
Data Index: 93009 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8205. Min Range: -5.8205
Max Act: 5.3830. Min Act: -0.1700
Data Index: 4191795 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8205. Min Range: -5.8205
Max Act: 5.3518. Min Act: -0.1700
Data Index: 5260327 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8205. Min Range: -5.8205
Max Act: 5.3205. Min Act: -0.1700
Data Index: 2738187 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8205. Min Range: -5.8205
Max Act: 5.3205. Min Act: -0.1700
Data Index: 1298769 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8205. Min Range: -5.8205
Max Act: 5.2268. Min Act: -0.1700
Data Index: 196779 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8205. Min Range: -5.8205
Max Act: 5.2580. Min Act: -0.1700
Data Index: 484615 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8205. Min Range: -5.8205
Max Act: 5.2268. Min Act: -0.1700
Data Index: 2644890 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8205. Min Range: -5.8205
Max Act: 5.1955. Min Act: -0.1700
Data Index: 460544 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8205. Min Range: -5.8205
Max Act: 5.1643. Min Act: -0.1700
Data Index: 4487735 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8205. Min Range: -5.8205
Max Act: 5.1643. Min Act: -0.1700
Data Index: 3274081 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8205. Min Range: -5.8205
Max Act: 5.1643. Min Act: -0.1700
Data Index: 5915369 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8205. Min Range: -5.8205
Max Act: 5.1330. Min Act: -0.1700
Data Index: 2376946 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8205. Min Range: -5.8205
Max Act: 5.1018. Min Act: -0.1700
Data Index: 3928207 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8205. Min Range: -5.8205
Max Act: 5.1330. Min Act: -0.1700
Data Index: 3306334 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8205. Min Range: -5.8205
Max Act: 5.1330. Min Act: -0.1700
Data Index: 6211652 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19