Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5175 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1142. Min Range: -6.1142
Max Act: 6.1142. Min Act: -0.1700
Data Index: 401924 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1142. Min Range: -6.1142
Max Act: 6.0205. Min Act: -0.1700
Data Index: 6960398 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1142. Min Range: -6.1142
Max Act: 6.0205. Min Act: -0.1700
Data Index: 2397634 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1142. Min Range: -6.1142
Max Act: 6.0205. Min Act: -0.1700
Data Index: 3262372 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.9892. Min Act: -0.1700
Data Index: 5212016 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.9892. Min Act: -0.1700
Data Index: 2509663 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.9580. Min Act: -0.1700
Data Index: 7230352 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.9580. Min Act: -0.1700
Data Index: 8523838 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.9267. Min Act: -0.1700
Data Index: 5471336 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.8955. Min Act: -0.1700
Data Index: 7036227 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.9267. Min Act: -0.1700
Data Index: 2569310 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.8330. Min Act: -0.1700
Data Index: 4299104 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.8017. Min Act: -0.1700
Data Index: 8180459 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.8017. Min Act: -0.1700
Data Index: 180323 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.8017. Min Act: -0.1700
Data Index: 2285952 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.7705. Min Act: -0.1700
Data Index: 857754 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.8017. Min Act: -0.1700
Data Index: 3074341 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.8017. Min Act: -0.1700
Data Index: 2690628 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.8017. Min Act: -0.1700
Data Index: 2056059 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.7705. Min Act: -0.1700
Data Index: 3689065 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19