Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 413 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0572. Min Range: -7.0572
Max Act: 7.0572. Min Act: -0.1700
Data Index: 1220055 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0572. Min Range: -7.0572
Max Act: 6.8072. Min Act: -0.1700
Data Index: 7678832 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0572. Min Range: -7.0572
Max Act: 6.8072. Min Act: -0.1700
Data Index: 4015065 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0572. Min Range: -7.0572
Max Act: 6.7447. Min Act: -0.1700
Data Index: 1695862 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0572. Min Range: -7.0572
Max Act: 6.7135. Min Act: -0.1700
Data Index: 1852662 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0572. Min Range: -7.0572
Max Act: 6.6822. Min Act: -0.1700
Data Index: 8013480 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0572. Min Range: -7.0572
Max Act: 6.6510. Min Act: -0.1700
Data Index: 8615234 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0572. Min Range: -7.0572
Max Act: 6.6510. Min Act: -0.1700
Data Index: 8688621 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0572. Min Range: -7.0572
Max Act: 6.6510. Min Act: -0.1700
Data Index: 3660839 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0572. Min Range: -7.0572
Max Act: 6.6822. Min Act: -0.1700
Data Index: 3631954 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0572. Min Range: -7.0572
Max Act: 6.6510. Min Act: -0.1700
Data Index: 715037 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0572. Min Range: -7.0572
Max Act: 6.6510. Min Act: -0.1700
Data Index: 902496 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0572. Min Range: -7.0572
Max Act: 6.6510. Min Act: -0.1700
Data Index: 4279244 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0572. Min Range: -7.0572
Max Act: 6.6197. Min Act: -0.1700
Data Index: 3579807 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0572. Min Range: -7.0572
Max Act: 6.6510. Min Act: -0.1700
Data Index: 1193313 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0572. Min Range: -7.0572
Max Act: 6.5885. Min Act: -0.1700
Data Index: 4557294 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0572. Min Range: -7.0572
Max Act: 6.6197. Min Act: -0.1700
Data Index: 1975632 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0572. Min Range: -7.0572
Max Act: 6.5885. Min Act: -0.1700
Data Index: 6790582 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0572. Min Range: -7.0572
Max Act: 6.5885. Min Act: -0.1700
Data Index: 8767726 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0572. Min Range: -7.0572
Max Act: 6.5885. Min Act: -0.1700
Data Index: 4565796 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19