Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 481 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1107. Min Range: -7.1107
Max Act: 7.1107. Min Act: -0.1700
Data Index: 4108709 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1107. Min Range: -7.1107
Max Act: 6.8920. Min Act: -0.1700
Data Index: 5639747 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1107. Min Range: -7.1107
Max Act: 6.7982. Min Act: -0.1700
Data Index: 2853380 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1107. Min Range: -7.1107
Max Act: 6.7670. Min Act: -0.1700
Data Index: 5077280 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1107. Min Range: -7.1107
Max Act: 6.7357. Min Act: -0.1700
Data Index: 5139792 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1107. Min Range: -7.1107
Max Act: 6.7045. Min Act: -0.1700
Data Index: 2211056 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1107. Min Range: -7.1107
Max Act: 6.6420. Min Act: -0.1700
Data Index: 6924725 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1107. Min Range: -7.1107
Max Act: 6.6420. Min Act: -0.1700
Data Index: 2300115 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1107. Min Range: -7.1107
Max Act: 6.6420. Min Act: -0.1700
Data Index: 326455 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1107. Min Range: -7.1107
Max Act: 6.6420. Min Act: -0.1700
Data Index: 258147 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1107. Min Range: -7.1107
Max Act: 6.6420. Min Act: -0.1700
Data Index: 1499778 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1107. Min Range: -7.1107
Max Act: 6.6107. Min Act: -0.1700
Data Index: 5703038 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1107. Min Range: -7.1107
Max Act: 6.6107. Min Act: -0.1700
Data Index: 1609555 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1107. Min Range: -7.1107
Max Act: 6.5795. Min Act: -0.1700
Data Index: 4438856 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1107. Min Range: -7.1107
Max Act: 6.5795. Min Act: -0.1700
Data Index: 5829630 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1107. Min Range: -7.1107
Max Act: 6.6107. Min Act: -0.1700
Data Index: 6256962 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1107. Min Range: -7.1107
Max Act: 6.5482. Min Act: -0.1700
Data Index: 5328361 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1107. Min Range: -7.1107
Max Act: 6.5482. Min Act: -0.1700
Data Index: 1356413 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1107. Min Range: -7.1107
Max Act: 6.5482. Min Act: -0.1700
Data Index: 6896322 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1107. Min Range: -7.1107
Max Act: 6.5795. Min Act: -0.1700
Data Index: 7259427 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19