Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1346 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6107. Min Range: -6.6107
Max Act: 6.6107. Min Act: -0.1700
Data Index: 7186947 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6107. Min Range: -6.6107
Max Act: 6.2045. Min Act: -0.1700
Data Index: 4909107 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6107. Min Range: -6.6107
Max Act: 6.1107. Min Act: -0.1700
Data Index: 3213005 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6107. Min Range: -6.6107
Max Act: 6.0795. Min Act: -0.1700
Data Index: 3409673 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6107. Min Range: -6.6107
Max Act: 6.0795. Min Act: -0.1700
Data Index: 8027107 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6107. Min Range: -6.6107
Max Act: 6.0482. Min Act: -0.1700
Data Index: 8601127 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6107. Min Range: -6.6107
Max Act: 5.9857. Min Act: -0.1700
Data Index: 2035118 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6107. Min Range: -6.6107
Max Act: 5.9545. Min Act: -0.1700
Data Index: 7227840 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6107. Min Range: -6.6107
Max Act: 5.9232. Min Act: -0.1700
Data Index: 637158 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6107. Min Range: -6.6107
Max Act: 5.9232. Min Act: -0.1700
Data Index: 2241598 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6107. Min Range: -6.6107
Max Act: 5.9232. Min Act: -0.1700
Data Index: 5034318 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6107. Min Range: -6.6107
Max Act: 5.8920. Min Act: -0.1700
Data Index: 6357095 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6107. Min Range: -6.6107
Max Act: 5.9232. Min Act: -0.1700
Data Index: 7322419 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6107. Min Range: -6.6107
Max Act: 5.8295. Min Act: -0.1700
Data Index: 1086017 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6107. Min Range: -6.6107
Max Act: 5.8295. Min Act: -0.1700
Data Index: 4757570 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6107. Min Range: -6.6107
Max Act: 5.8295. Min Act: -0.1700
Data Index: 1947953 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6107. Min Range: -6.6107
Max Act: 5.8607. Min Act: -0.1700
Data Index: 905271 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6107. Min Range: -6.6107
Max Act: 5.7982. Min Act: -0.1700
Data Index: 4026898 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6107. Min Range: -6.6107
Max Act: 5.7670. Min Act: -0.1700
Data Index: 6977137 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6107. Min Range: -6.6107
Max Act: 5.7982. Min Act: -0.1700
Data Index: 1677528 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19