Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3068 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6174. Min Range: -8.6174
Max Act: 8.6174. Min Act: -0.1700
Data Index: 5128604 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6174. Min Range: -8.6174
Max Act: 8.4924. Min Act: -0.1700
Data Index: 1212678 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6174. Min Range: -8.6174
Max Act: 8.3674. Min Act: -0.1700
Data Index: 3676833 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6174. Min Range: -8.6174
Max Act: 8.3674. Min Act: -0.1700
Data Index: 8348538 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6174. Min Range: -8.6174
Max Act: 8.3049. Min Act: -0.1700
Data Index: 7569171 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6174. Min Range: -8.6174
Max Act: 8.3049. Min Act: -0.1700
Data Index: 2098432 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6174. Min Range: -8.6174
Max Act: 8.2424. Min Act: -0.1700
Data Index: 4565817 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6174. Min Range: -8.6174
Max Act: 8.1799. Min Act: -0.1700
Data Index: 2824038 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6174. Min Range: -8.6174
Max Act: 8.1799. Min Act: -0.1700
Data Index: 7960379 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6174. Min Range: -8.6174
Max Act: 8.1799. Min Act: -0.1700
Data Index: 2505211 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6174. Min Range: -8.6174
Max Act: 8.1174. Min Act: -0.1700
Data Index: 5110232 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6174. Min Range: -8.6174
Max Act: 8.1799. Min Act: -0.1700
Data Index: 316980 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6174. Min Range: -8.6174
Max Act: 8.1799. Min Act: -0.1700
Data Index: 8086752 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6174. Min Range: -8.6174
Max Act: 8.1174. Min Act: -0.1700
Data Index: 5291656 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6174. Min Range: -8.6174
Max Act: 8.1174. Min Act: -0.1700
Data Index: 3787489 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6174. Min Range: -8.6174
Max Act: 8.1174. Min Act: -0.1700
Data Index: 6305106 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6174. Min Range: -8.6174
Max Act: 8.1174. Min Act: -0.1700
Data Index: 5717226 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6174. Min Range: -8.6174
Max Act: 8.0549. Min Act: -0.1700
Data Index: 4115105 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6174. Min Range: -8.6174
Max Act: 8.0549. Min Act: -0.1700
Data Index: 6012536 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6174. Min Range: -8.6174
Max Act: 7.9924. Min Act: -0.1700
Data Index: 251767 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19