Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3347 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7157. Min Range: -7.7157
Max Act: 7.7157. Min Act: -0.1700
Data Index: 7068416 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7157. Min Range: -7.7157
Max Act: 7.4344. Min Act: -0.1700
Data Index: 718311 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7157. Min Range: -7.7157
Max Act: 7.4032. Min Act: -0.1700
Data Index: 718310 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7157. Min Range: -7.7157
Max Act: 7.4344. Min Act: -0.1700
Data Index: 3488200 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7157. Min Range: -7.7157
Max Act: 7.2782. Min Act: -0.1700
Data Index: 6223362 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7157. Min Range: -7.7157
Max Act: 7.2782. Min Act: -0.1700
Data Index: 3547273 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7157. Min Range: -7.7157
Max Act: 7.2782. Min Act: -0.1700
Data Index: 6063626 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7157. Min Range: -7.7157
Max Act: 7.2157. Min Act: -0.1700
Data Index: 1784457 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7157. Min Range: -7.7157
Max Act: 7.1844. Min Act: -0.1700
Data Index: 1784464 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7157. Min Range: -7.7157
Max Act: 7.1219. Min Act: -0.1700
Data Index: 1784458 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7157. Min Range: -7.7157
Max Act: 7.1219. Min Act: -0.1700
Data Index: 263715 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7157. Min Range: -7.7157
Max Act: 7.0907. Min Act: -0.1700
Data Index: 7059812 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7157. Min Range: -7.7157
Max Act: 7.1219. Min Act: -0.1700
Data Index: 6063625 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7157. Min Range: -7.7157
Max Act: 7.0907. Min Act: -0.1700
Data Index: 6063633 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7157. Min Range: -7.7157
Max Act: 7.0907. Min Act: -0.1700
Data Index: 1784465 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7157. Min Range: -7.7157
Max Act: 7.0907. Min Act: -0.1700
Data Index: 3544396 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7157. Min Range: -7.7157
Max Act: 7.0907. Min Act: -0.1700
Data Index: 8181645 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7157. Min Range: -7.7157
Max Act: 7.0594. Min Act: -0.1700
Data Index: 8181635 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7157. Min Range: -7.7157
Max Act: 7.0907. Min Act: -0.1700
Data Index: 1976122 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7157. Min Range: -7.7157
Max Act: 7.0594. Min Act: -0.1700
Data Index: 8181632 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19