Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3013 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7134. Min Range: -6.7134
Max Act: 6.7134. Min Act: -0.1700
Data Index: 766463 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7134. Min Range: -6.7134
Max Act: 6.2447. Min Act: -0.1700
Data Index: 788096 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7134. Min Range: -6.7134
Max Act: 6.2759. Min Act: -0.1700
Data Index: 4286332 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7134. Min Range: -6.7134
Max Act: 6.2447. Min Act: -0.1700
Data Index: 8405455 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7134. Min Range: -6.7134
Max Act: 6.1822. Min Act: -0.1700
Data Index: 4211197 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7134. Min Range: -6.7134
Max Act: 6.1197. Min Act: -0.1700
Data Index: 1090943 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7134. Min Range: -6.7134
Max Act: 6.1197. Min Act: -0.1700
Data Index: 4828905 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7134. Min Range: -6.7134
Max Act: 6.1197. Min Act: -0.1700
Data Index: 3795357 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7134. Min Range: -6.7134
Max Act: 6.1197. Min Act: -0.1700
Data Index: 4008401 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7134. Min Range: -6.7134
Max Act: 6.0259. Min Act: -0.1700
Data Index: 7175726 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7134. Min Range: -6.7134
Max Act: 5.9947. Min Act: -0.1700
Data Index: 4351437 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7134. Min Range: -6.7134
Max Act: 5.9634. Min Act: -0.1700
Data Index: 2280119 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7134. Min Range: -6.7134
Max Act: 5.9322. Min Act: -0.1700
Data Index: 2842517 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7134. Min Range: -6.7134
Max Act: 5.9322. Min Act: -0.1700
Data Index: 4107222 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7134. Min Range: -6.7134
Max Act: 5.9634. Min Act: -0.1700
Data Index: 5376712 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7134. Min Range: -6.7134
Max Act: 5.9634. Min Act: -0.1700
Data Index: 7652628 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7134. Min Range: -6.7134
Max Act: 5.8697. Min Act: -0.1700
Data Index: 3911155 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7134. Min Range: -6.7134
Max Act: 5.8697. Min Act: -0.1700
Data Index: 7926034 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7134. Min Range: -6.7134
Max Act: 5.8697. Min Act: -0.1700
Data Index: 1084143 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7134. Min Range: -6.7134
Max Act: 5.8384. Min Act: -0.1700
Data Index: 5006528 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19