Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3992 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.5944. Min Act: -0.1700
Data Index: 132339 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.5632. Min Act: -0.1700
Data Index: 6676325 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.3757. Min Act: -0.1700
Data Index: 132342 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.3444. Min Act: -0.1700
Data Index: 190117 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.3132. Min Act: -0.1700
Data Index: 1270526 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.2507. Min Act: -0.1700
Data Index: 6900823 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.1882. Min Act: -0.1700
Data Index: 3310701 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.1257. Min Act: -0.1700
Data Index: 3614065 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.1569. Min Act: -0.1700
Data Index: 7308452 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.1569. Min Act: -0.1700
Data Index: 6020198 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.1257. Min Act: -0.1700
Data Index: 5062771 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.1257. Min Act: -0.1700
Data Index: 7075384 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.1257. Min Act: -0.1700
Data Index: 8224693 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.0944. Min Act: -0.1700
Data Index: 7398614 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.1257. Min Act: -0.1700
Data Index: 6233525 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.0944. Min Act: -0.1700
Data Index: 8766762 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.0944. Min Act: -0.1700
Data Index: 7825825 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.0944. Min Act: -0.1700
Data Index: 3989675 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.0944. Min Act: -0.1700
Data Index: 1648729 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.0632. Min Act: -0.1700
Data Index: 3606301 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19