Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5537 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 24.8284. Min Range: -24.8284
Max Act: 24.8284. Min Act: -0.1700
Data Index: 7743387 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 24.8284. Min Range: -24.8284
Max Act: 24.5784. Min Act: -0.1700
Data Index: 20175 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 24.8284. Min Range: -24.8284
Max Act: 24.4534. Min Act: -0.1700
Data Index: 4700831 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 24.8284. Min Range: -24.8284
Max Act: 24.3284. Min Act: -0.1700
Data Index: 2438037 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 24.8284. Min Range: -24.8284
Max Act: 24.3284. Min Act: -0.1700
Data Index: 4218136 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 24.8284. Min Range: -24.8284
Max Act: 24.3284. Min Act: -0.1700
Data Index: 8818125 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 24.8284. Min Range: -24.8284
Max Act: 24.2034. Min Act: -0.1700
Data Index: 8818129 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 24.8284. Min Range: -24.8284
Max Act: 24.2034. Min Act: -0.1700
Data Index: 4745072 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 24.8284. Min Range: -24.8284
Max Act: 24.2034. Min Act: -0.1700
Data Index: 38549 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 24.8284. Min Range: -24.8284
Max Act: 24.2034. Min Act: -0.1700
Data Index: 3759175 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 24.8284. Min Range: -24.8284
Max Act: 24.0784. Min Act: -0.1700
Data Index: 38555 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 24.8284. Min Range: -24.8284
Max Act: 23.9534. Min Act: -0.1700
Data Index: 523340 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 24.8284. Min Range: -24.8284
Max Act: 23.8284. Min Act: -0.1700
Data Index: 7743392 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 24.8284. Min Range: -24.8284
Max Act: 23.7034. Min Act: -0.1700
Data Index: 3759183 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 24.8284. Min Range: -24.8284
Max Act: 23.8284. Min Act: -0.1700
Data Index: 4582921 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 24.8284. Min Range: -24.8284
Max Act: 23.8284. Min Act: -0.1700
Data Index: 7743396 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 24.8284. Min Range: -24.8284
Max Act: 23.7034. Min Act: -0.1700
Data Index: 2021931 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 24.8284. Min Range: -24.8284
Max Act: 23.7034. Min Act: -0.1700
Data Index: 4266095 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 24.8284. Min Range: -24.8284
Max Act: 23.7034. Min Act: -0.1700
Data Index: 4745077 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 24.8284. Min Range: -24.8284
Max Act: 23.7034. Min Act: -0.1700
Data Index: 3759185 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19