Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4944 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.8532. Min Act: -0.1700
Data Index: 4281675 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.7282. Min Act: -0.1700
Data Index: 7745988 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.6657. Min Act: -0.1700
Data Index: 8639980 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.6032. Min Act: -0.1700
Data Index: 2311939 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.5720. Min Act: -0.1700
Data Index: 5009348 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.5407. Min Act: -0.1700
Data Index: 1316940 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.5094. Min Act: -0.1700
Data Index: 6886205 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.5094. Min Act: -0.1700
Data Index: 8195051 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.3844. Min Act: -0.1700
Data Index: 4580002 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.4469. Min Act: -0.1700
Data Index: 259953 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.4157. Min Act: -0.1700
Data Index: 5463019 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.4469. Min Act: -0.1700
Data Index: 2205783 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.4157. Min Act: -0.1700
Data Index: 2205782 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.4157. Min Act: -0.1700
Data Index: 7038441 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.4157. Min Act: -0.1700
Data Index: 6121079 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.3844. Min Act: -0.1700
Data Index: 1040854 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.3532. Min Act: -0.1700
Data Index: 7649723 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.3532. Min Act: -0.1700
Data Index: 7906439 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.3844. Min Act: -0.1700
Data Index: 5594320 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.3844. Min Act: -0.1700
Data Index: 7965229 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19