Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2282. Min Range: -4.2282
Max Act: 4.2282. Min Act: -0.1700
Data Index: 2012800 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2282. Min Range: -4.2282
Max Act: 4.1657. Min Act: -0.1700
Data Index: 1023031 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2282. Min Range: -4.2282
Max Act: 4.1344. Min Act: -0.1700
Data Index: 1923891 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2282. Min Range: -4.2282
Max Act: 4.1032. Min Act: -0.1700
Data Index: 8030608 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2282. Min Range: -4.2282
Max Act: 4.0719. Min Act: -0.1700
Data Index: 3855347 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2282. Min Range: -4.2282
Max Act: 4.0094. Min Act: -0.1700
Data Index: 7322375 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2282. Min Range: -4.2282
Max Act: 4.0094. Min Act: -0.1700
Data Index: 2941310 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2282. Min Range: -4.2282
Max Act: 4.0094. Min Act: -0.1700
Data Index: 3164489 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2282. Min Range: -4.2282
Max Act: 3.9469. Min Act: -0.1700
Data Index: 2617162 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2282. Min Range: -4.2282
Max Act: 3.9781. Min Act: -0.1700
Data Index: 4318872 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2282. Min Range: -4.2282
Max Act: 3.9781. Min Act: -0.1700
Data Index: 1142656 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2282. Min Range: -4.2282
Max Act: 3.9469. Min Act: -0.1700
Data Index: 8729203 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2282. Min Range: -4.2282
Max Act: 3.9469. Min Act: -0.1700
Data Index: 6085190 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2282. Min Range: -4.2282
Max Act: 3.9469. Min Act: -0.1700
Data Index: 8077811 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2282. Min Range: -4.2282
Max Act: 3.9156. Min Act: -0.1700
Data Index: 8116964 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2282. Min Range: -4.2282
Max Act: 3.8843. Min Act: -0.1700
Data Index: 6475368 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2282. Min Range: -4.2282
Max Act: 3.8843. Min Act: -0.1700
Data Index: 5753800 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2282. Min Range: -4.2282
Max Act: 3.9156. Min Act: -0.1700
Data Index: 164557 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2282. Min Range: -4.2282
Max Act: 3.8843. Min Act: -0.1700
Data Index: 888483 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2282. Min Range: -4.2282
Max Act: 3.8843. Min Act: -0.1700
Data Index: 5593748 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19