Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3446 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8528. Min Range: -6.8528
Max Act: 6.8528. Min Act: -0.1700
Data Index: 7562389 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8528. Min Range: -6.8528
Max Act: 6.6966. Min Act: -0.1700
Data Index: 7646974 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8528. Min Range: -6.8528
Max Act: 6.4778. Min Act: -0.1700
Data Index: 903792 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8528. Min Range: -6.8528
Max Act: 6.3528. Min Act: -0.1700
Data Index: 5853780 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8528. Min Range: -6.8528
Max Act: 6.2591. Min Act: -0.1700
Data Index: 1987130 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8528. Min Range: -6.8528
Max Act: 6.1966. Min Act: -0.1700
Data Index: 6709805 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8528. Min Range: -6.8528
Max Act: 6.1341. Min Act: -0.1700
Data Index: 5531177 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8528. Min Range: -6.8528
Max Act: 6.1028. Min Act: -0.1700
Data Index: 3198713 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8528. Min Range: -6.8528
Max Act: 6.1341. Min Act: -0.1700
Data Index: 1309608 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8528. Min Range: -6.8528
Max Act: 6.1341. Min Act: -0.1700
Data Index: 6537056 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8528. Min Range: -6.8528
Max Act: 6.1341. Min Act: -0.1700
Data Index: 7449516 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8528. Min Range: -6.8528
Max Act: 6.1028. Min Act: -0.1700
Data Index: 3198714 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8528. Min Range: -6.8528
Max Act: 6.1028. Min Act: -0.1700
Data Index: 3821269 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8528. Min Range: -6.8528
Max Act: 6.0716. Min Act: -0.1700
Data Index: 6841031 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8528. Min Range: -6.8528
Max Act: 6.0403. Min Act: -0.1700
Data Index: 1277665 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8528. Min Range: -6.8528
Max Act: 6.0716. Min Act: -0.1700
Data Index: 7705136 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8528. Min Range: -6.8528
Max Act: 6.0091. Min Act: -0.1700
Data Index: 1170037 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8528. Min Range: -6.8528
Max Act: 6.0091. Min Act: -0.1700
Data Index: 2726002 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8528. Min Range: -6.8528
Max Act: 5.9778. Min Act: -0.1700
Data Index: 403740 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8528. Min Range: -6.8528
Max Act: 5.9778. Min Act: -0.1700
Data Index: 4377461 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19