Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2106 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.8489. Min Act: -0.1700
Data Index: 7918496 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.6302. Min Act: -0.1700
Data Index: 6232045 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.6302. Min Act: -0.1700
Data Index: 4170987 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.5989. Min Act: -0.1700
Data Index: 2380555 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.5364. Min Act: -0.1700
Data Index: 4787451 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.5052. Min Act: -0.1700
Data Index: 1687965 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.4114. Min Act: -0.1700
Data Index: 6453917 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.3177. Min Act: -0.1700
Data Index: 1479301 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.3489. Min Act: -0.1700
Data Index: 1021855 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.3177. Min Act: -0.1700
Data Index: 2210274 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.2864. Min Act: -0.1700
Data Index: 5030595 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.2239. Min Act: -0.1700
Data Index: 923922 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.2239. Min Act: -0.1700
Data Index: 1283867 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.2239. Min Act: -0.1700
Data Index: 3692015 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.1927. Min Act: -0.1700
Data Index: 4879047 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.1927. Min Act: -0.1700
Data Index: 5426039 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.2239. Min Act: -0.1700
Data Index: 3546634 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.1614. Min Act: -0.1700
Data Index: 2299299 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.1614. Min Act: -0.1700
Data Index: 2301681 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8489. Min Range: -5.8489
Max Act: 5.1614. Min Act: -0.1700
Data Index: 8386587 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19