Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 205 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2838. Min Range: -6.2838
Max Act: 6.2838. Min Act: -0.1700
Data Index: 7245217 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2838. Min Range: -6.2838
Max Act: 6.2525. Min Act: -0.1700
Data Index: 3202820 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2838. Min Range: -6.2838
Max Act: 6.2213. Min Act: -0.1700
Data Index: 6679384 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2838. Min Range: -6.2838
Max Act: 6.1900. Min Act: -0.1700
Data Index: 2206804 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2838. Min Range: -6.2838
Max Act: 6.1275. Min Act: -0.1700
Data Index: 2301798 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2838. Min Range: -6.2838
Max Act: 6.0963. Min Act: -0.1700
Data Index: 3424600 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2838. Min Range: -6.2838
Max Act: 6.0650. Min Act: -0.1700
Data Index: 4859067 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2838. Min Range: -6.2838
Max Act: 6.0650. Min Act: -0.1700
Data Index: 6885005 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2838. Min Range: -6.2838
Max Act: 6.0338. Min Act: -0.1700
Data Index: 3860758 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2838. Min Range: -6.2838
Max Act: 6.0338. Min Act: -0.1700
Data Index: 4069126 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2838. Min Range: -6.2838
Max Act: 6.0025. Min Act: -0.1700
Data Index: 7177602 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2838. Min Range: -6.2838
Max Act: 5.9400. Min Act: -0.1700
Data Index: 8509718 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2838. Min Range: -6.2838
Max Act: 5.9400. Min Act: -0.1700
Data Index: 1322040 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2838. Min Range: -6.2838
Max Act: 5.8775. Min Act: -0.1700
Data Index: 8687314 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2838. Min Range: -6.2838
Max Act: 5.8775. Min Act: -0.1700
Data Index: 210695 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2838. Min Range: -6.2838
Max Act: 5.8463. Min Act: -0.1700
Data Index: 975837 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2838. Min Range: -6.2838
Max Act: 5.7838. Min Act: -0.1700
Data Index: 4301176 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2838. Min Range: -6.2838
Max Act: 5.8150. Min Act: -0.1700
Data Index: 7423140 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2838. Min Range: -6.2838
Max Act: 5.7838. Min Act: -0.1700
Data Index: 986358 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2838. Min Range: -6.2838
Max Act: 5.8150. Min Act: -0.1700
Data Index: 4087888 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19