Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6376 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4208. Min Range: -7.4208
Max Act: 7.4208. Min Act: -0.1700
Data Index: 3728123 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4208. Min Range: -7.4208
Max Act: 7.3895. Min Act: -0.1700
Data Index: 1522044 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4208. Min Range: -7.4208
Max Act: 7.3583. Min Act: -0.1700
Data Index: 6262679 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4208. Min Range: -7.4208
Max Act: 7.3583. Min Act: -0.1700
Data Index: 4610684 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4208. Min Range: -7.4208
Max Act: 7.3270. Min Act: -0.1700
Data Index: 2199133 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4208. Min Range: -7.4208
Max Act: 7.2958. Min Act: -0.1700
Data Index: 1978541 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4208. Min Range: -7.4208
Max Act: 7.2958. Min Act: -0.1700
Data Index: 2290750 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4208. Min Range: -7.4208
Max Act: 7.2333. Min Act: -0.1700
Data Index: 1626620 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4208. Min Range: -7.4208
Max Act: 7.2333. Min Act: -0.1700
Data Index: 6037443 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4208. Min Range: -7.4208
Max Act: 7.2333. Min Act: -0.1700
Data Index: 3200650 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4208. Min Range: -7.4208
Max Act: 7.2020. Min Act: -0.1700
Data Index: 3355045 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4208. Min Range: -7.4208
Max Act: 7.1395. Min Act: -0.1700
Data Index: 3493029 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4208. Min Range: -7.4208
Max Act: 7.1395. Min Act: -0.1700
Data Index: 989210 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4208. Min Range: -7.4208
Max Act: 7.1395. Min Act: -0.1700
Data Index: 1946359 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4208. Min Range: -7.4208
Max Act: 7.1083. Min Act: -0.1700
Data Index: 8804586 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4208. Min Range: -7.4208
Max Act: 7.1395. Min Act: -0.1700
Data Index: 7461963 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4208. Min Range: -7.4208
Max Act: 7.1395. Min Act: -0.1700
Data Index: 2649404 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4208. Min Range: -7.4208
Max Act: 7.1083. Min Act: -0.1700
Data Index: 3827506 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4208. Min Range: -7.4208
Max Act: 7.1395. Min Act: -0.1700
Data Index: 8437153 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4208. Min Range: -7.4208
Max Act: 7.1083. Min Act: -0.1700
Data Index: 1146792 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19