Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6094 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0072. Min Range: -10.0072
Max Act: 10.0072. Min Act: -0.1700
Data Index: 4784010 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0072. Min Range: -10.0072
Max Act: 9.6322. Min Act: -0.1700
Data Index: 4067962 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0072. Min Range: -10.0072
Max Act: 9.1947. Min Act: -0.1700
Data Index: 5202708 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0072. Min Range: -10.0072
Max Act: 9.1322. Min Act: -0.1700
Data Index: 302265 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0072. Min Range: -10.0072
Max Act: 9.0072. Min Act: -0.1700
Data Index: 6860244 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0072. Min Range: -10.0072
Max Act: 8.9447. Min Act: -0.1700
Data Index: 3889208 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0072. Min Range: -10.0072
Max Act: 8.8822. Min Act: -0.1700
Data Index: 4073889 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0072. Min Range: -10.0072
Max Act: 8.8822. Min Act: -0.1700
Data Index: 3958145 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0072. Min Range: -10.0072
Max Act: 8.8822. Min Act: -0.1700
Data Index: 8453738 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0072. Min Range: -10.0072
Max Act: 8.8197. Min Act: -0.1700
Data Index: 4650056 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0072. Min Range: -10.0072
Max Act: 8.8197. Min Act: -0.1700
Data Index: 6832448 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0072. Min Range: -10.0072
Max Act: 8.7572. Min Act: -0.1700
Data Index: 3129549 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0072. Min Range: -10.0072
Max Act: 8.7572. Min Act: -0.1700
Data Index: 8723628 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0072. Min Range: -10.0072
Max Act: 8.6947. Min Act: -0.1700
Data Index: 4185356 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0072. Min Range: -10.0072
Max Act: 8.7572. Min Act: -0.1700
Data Index: 7571844 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0072. Min Range: -10.0072
Max Act: 8.7572. Min Act: -0.1700
Data Index: 906281 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0072. Min Range: -10.0072
Max Act: 8.7572. Min Act: -0.1700
Data Index: 1040819 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0072. Min Range: -10.0072
Max Act: 8.7572. Min Act: -0.1700
Data Index: 4747379 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0072. Min Range: -10.0072
Max Act: 8.7572. Min Act: -0.1700
Data Index: 364474 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0072. Min Range: -10.0072
Max Act: 8.6947. Min Act: -0.1700
Data Index: 1592354 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19