Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3746 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6544. Min Range: -3.6544
Max Act: 3.6544. Min Act: -0.1700
Data Index: 3193995 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6544. Min Range: -3.6544
Max Act: 3.6544. Min Act: -0.1700
Data Index: 5545758 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6544. Min Range: -3.6544
Max Act: 3.6388. Min Act: -0.1700
Data Index: 1627027 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6544. Min Range: -3.6544
Max Act: 3.6388. Min Act: -0.1700
Data Index: 4683858 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6544. Min Range: -3.6544
Max Act: 3.5918. Min Act: -0.1700
Data Index: 5633939 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6544. Min Range: -3.6544
Max Act: 3.5918. Min Act: -0.1700
Data Index: 277983 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6544. Min Range: -3.6544
Max Act: 3.5762. Min Act: -0.1700
Data Index: 6940073 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6544. Min Range: -3.6544
Max Act: 3.5605. Min Act: -0.1700
Data Index: 4269702 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6544. Min Range: -3.6544
Max Act: 3.5448. Min Act: -0.1700
Data Index: 3014952 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6544. Min Range: -3.6544
Max Act: 3.5605. Min Act: -0.1700
Data Index: 2499537 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6544. Min Range: -3.6544
Max Act: 3.5292. Min Act: -0.1700
Data Index: 1054162 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6544. Min Range: -3.6544
Max Act: 3.5292. Min Act: -0.1700
Data Index: 3814184 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6544. Min Range: -3.6544
Max Act: 3.5292. Min Act: -0.1700
Data Index: 4396896 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6544. Min Range: -3.6544
Max Act: 3.5448. Min Act: -0.1700
Data Index: 3080791 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6544. Min Range: -3.6544
Max Act: 3.5292. Min Act: -0.1700
Data Index: 7156570 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6544. Min Range: -3.6544
Max Act: 3.5135. Min Act: -0.1700
Data Index: 4279653 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6544. Min Range: -3.6544
Max Act: 3.5292. Min Act: -0.1700
Data Index: 653622 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6544. Min Range: -3.6544
Max Act: 3.4979. Min Act: -0.1700
Data Index: 6106196 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6544. Min Range: -3.6544
Max Act: 3.4979. Min Act: -0.1700
Data Index: 4084387 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6544. Min Range: -3.6544
Max Act: 3.4822. Min Act: -0.1700
Data Index: 2523074 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19