Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1316 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7201. Min Range: -10.7201
Max Act: 10.7201. Min Act: -0.1700
Data Index: 6777200 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7201. Min Range: -10.7201
Max Act: 10.2826. Min Act: -0.1700
Data Index: 6532506 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7201. Min Range: -10.7201
Max Act: 10.0951. Min Act: -0.1700
Data Index: 8346939 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7201. Min Range: -10.7201
Max Act: 9.9701. Min Act: -0.1700
Data Index: 5276974 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7201. Min Range: -10.7201
Max Act: 9.9076. Min Act: -0.1700
Data Index: 8243917 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7201. Min Range: -10.7201
Max Act: 9.8451. Min Act: -0.1700
Data Index: 1850829 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7201. Min Range: -10.7201
Max Act: 9.7826. Min Act: -0.1700
Data Index: 5778461 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7201. Min Range: -10.7201
Max Act: 9.9076. Min Act: -0.1700
Data Index: 1437947 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7201. Min Range: -10.7201
Max Act: 9.8451. Min Act: -0.1700
Data Index: 479047 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7201. Min Range: -10.7201
Max Act: 9.7826. Min Act: -0.1700
Data Index: 2747745 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7201. Min Range: -10.7201
Max Act: 9.7826. Min Act: -0.1700
Data Index: 4709557 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7201. Min Range: -10.7201
Max Act: 9.7826. Min Act: -0.1698
Data Index: 4754467 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7201. Min Range: -10.7201
Max Act: 9.7201. Min Act: -0.1700
Data Index: 8685854 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7201. Min Range: -10.7201
Max Act: 9.7201. Min Act: -0.1700
Data Index: 1590665 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7201. Min Range: -10.7201
Max Act: 9.7826. Min Act: -0.1700
Data Index: 7064053 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7201. Min Range: -10.7201
Max Act: 9.6576. Min Act: -0.1700
Data Index: 3075620 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7201. Min Range: -10.7201
Max Act: 9.7201. Min Act: -0.1699
Data Index: 2952920 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7201. Min Range: -10.7201
Max Act: 9.6576. Min Act: -0.1700
Data Index: 7791113 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7201. Min Range: -10.7201
Max Act: 9.6576. Min Act: -0.1700
Data Index: 1124776 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7201. Min Range: -10.7201
Max Act: 9.5951. Min Act: -0.1700
Data Index: 548088 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19