Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5097 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.7444. Min Range: -7.7444
Max Act: 7.7444. Min Act: -0.1700
Data Index: 7584119 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7444. Min Range: -7.7444
Max Act: 7.6194. Min Act: -0.1700
Data Index: 8656021 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7444. Min Range: -7.7444
Max Act: 7.6506. Min Act: -0.1700
Data Index: 1648884 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7444. Min Range: -7.7444
Max Act: 7.4319. Min Act: -0.1700
Data Index: 5711447 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7444. Min Range: -7.7444
Max Act: 7.3381. Min Act: -0.1700
Data Index: 7096160 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7444. Min Range: -7.7444
Max Act: 7.2756. Min Act: -0.1700
Data Index: 4095552 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7444. Min Range: -7.7444
Max Act: 7.2444. Min Act: -0.1700
Data Index: 505110 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7444. Min Range: -7.7444
Max Act: 7.1506. Min Act: -0.1700
Data Index: 7438124 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7444. Min Range: -7.7444
Max Act: 7.1506. Min Act: -0.1700
Data Index: 2951419 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7444. Min Range: -7.7444
Max Act: 7.1506. Min Act: -0.1700
Data Index: 6586062 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7444. Min Range: -7.7444
Max Act: 7.1194. Min Act: -0.1700
Data Index: 6294681 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7444. Min Range: -7.7444
Max Act: 7.0881. Min Act: -0.1700
Data Index: 2508117 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7444. Min Range: -7.7444
Max Act: 7.0569. Min Act: -0.1700
Data Index: 4921389 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7444. Min Range: -7.7444
Max Act: 7.0569. Min Act: -0.1700
Data Index: 2280990 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7444. Min Range: -7.7444
Max Act: 7.0256. Min Act: -0.1700
Data Index: 2412740 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7444. Min Range: -7.7444
Max Act: 6.9944. Min Act: -0.1700
Data Index: 8151453 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7444. Min Range: -7.7444
Max Act: 6.9944. Min Act: -0.1700
Data Index: 3094680 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7444. Min Range: -7.7444
Max Act: 6.9631. Min Act: -0.1700
Data Index: 4641427 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7444. Min Range: -7.7444
Max Act: 6.9631. Min Act: -0.1700
Data Index: 2201542 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7444. Min Range: -7.7444
Max Act: 6.9631. Min Act: -0.1700
Data Index: 2504687 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19