Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4358 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6862. Min Range: -6.6862
Max Act: 6.6862. Min Act: -0.1700
Data Index: 8643207 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6862. Min Range: -6.6862
Max Act: 6.3112. Min Act: -0.1700
Data Index: 3729410 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6862. Min Range: -6.6862
Max Act: 6.2487. Min Act: -0.1700
Data Index: 8451159 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6862. Min Range: -6.6862
Max Act: 6.2487. Min Act: -0.1700
Data Index: 6696184 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6862. Min Range: -6.6862
Max Act: 6.2174. Min Act: -0.1700
Data Index: 3509437 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6862. Min Range: -6.6862
Max Act: 6.1862. Min Act: -0.1700
Data Index: 3462832 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6862. Min Range: -6.6862
Max Act: 6.1549. Min Act: -0.1700
Data Index: 4641311 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6862. Min Range: -6.6862
Max Act: 6.1237. Min Act: -0.1700
Data Index: 5594137 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6862. Min Range: -6.6862
Max Act: 6.1549. Min Act: -0.1700
Data Index: 5944099 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6862. Min Range: -6.6862
Max Act: 5.9987. Min Act: -0.1700
Data Index: 8215164 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6862. Min Range: -6.6862
Max Act: 5.9674. Min Act: -0.1700
Data Index: 209377 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6862. Min Range: -6.6862
Max Act: 5.9362. Min Act: -0.1700
Data Index: 1563545 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6862. Min Range: -6.6862
Max Act: 5.9362. Min Act: -0.1700
Data Index: 4344693 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6862. Min Range: -6.6862
Max Act: 5.8424. Min Act: -0.1700
Data Index: 6500284 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6862. Min Range: -6.6862
Max Act: 5.8737. Min Act: -0.1700
Data Index: 3850445 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6862. Min Range: -6.6862
Max Act: 5.8424. Min Act: -0.1700
Data Index: 7794294 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6862. Min Range: -6.6862
Max Act: 5.8737. Min Act: -0.1700
Data Index: 8303935 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6862. Min Range: -6.6862
Max Act: 5.8737. Min Act: -0.1700
Data Index: 76259 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6862. Min Range: -6.6862
Max Act: 5.8112. Min Act: -0.1700
Data Index: 8588158 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6862. Min Range: -6.6862
Max Act: 5.8112. Min Act: -0.1700
Data Index: 7288870 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19