Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1925 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9188. Min Range: -1.9188
Max Act: 1.9188. Min Act: -0.1700
Data Index: 429219 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9188. Min Range: -1.9188
Max Act: 1.9017. Min Act: -0.1700
Data Index: 4204191 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9188. Min Range: -1.9188
Max Act: 1.9017. Min Act: -0.1700
Data Index: 6859085 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9188. Min Range: -1.9188
Max Act: 1.8847. Min Act: -0.1700
Data Index: 811041 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9188. Min Range: -1.9188
Max Act: 1.8847. Min Act: -0.1700
Data Index: 6018935 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9188. Min Range: -1.9188
Max Act: 1.8505. Min Act: -0.1700
Data Index: 6477668 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9188. Min Range: -1.9188
Max Act: 1.8505. Min Act: -0.1700
Data Index: 1506399 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9188. Min Range: -1.9188
Max Act: 1.8505. Min Act: -0.1700
Data Index: 4967179 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9188. Min Range: -1.9188
Max Act: 1.8333. Min Act: -0.1700
Data Index: 6739462 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9188. Min Range: -1.9188
Max Act: 1.8161. Min Act: -0.1700
Data Index: 3614696 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9188. Min Range: -1.9188
Max Act: 1.8161. Min Act: -0.1700
Data Index: 4547090 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9188. Min Range: -1.9188
Max Act: 1.8161. Min Act: -0.1700
Data Index: 264539 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9188. Min Range: -1.9188
Max Act: 1.8161. Min Act: -0.1700
Data Index: 87733 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9188. Min Range: -1.9188
Max Act: 1.7990. Min Act: -0.1700
Data Index: 5049622 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9188. Min Range: -1.9188
Max Act: 1.7990. Min Act: -0.1700
Data Index: 7145712 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9188. Min Range: -1.9188
Max Act: 1.7990. Min Act: -0.1700
Data Index: 6929717 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9188. Min Range: -1.9188
Max Act: 1.7990. Min Act: -0.1700
Data Index: 1599959 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9188. Min Range: -1.9188
Max Act: 1.7990. Min Act: -0.1700
Data Index: 3026096 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9188. Min Range: -1.9188
Max Act: 1.7817. Min Act: -0.1700
Data Index: 3783980 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9188. Min Range: -1.9188
Max Act: 1.7817. Min Act: -0.1700
Data Index: 2031701 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19