Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3818 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7467. Min Range: -4.7467
Max Act: 4.7467. Min Act: -0.1700
Data Index: 4371503 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7467. Min Range: -4.7467
Max Act: 4.6842. Min Act: -0.1700
Data Index: 200656 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7467. Min Range: -4.7467
Max Act: 4.6529. Min Act: -0.1700
Data Index: 1550824 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7467. Min Range: -4.7467
Max Act: 4.6529. Min Act: -0.1700
Data Index: 1063558 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7467. Min Range: -4.7467
Max Act: 4.6529. Min Act: -0.1700
Data Index: 3871247 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7467. Min Range: -4.7467
Max Act: 4.5904. Min Act: -0.1700
Data Index: 223242 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7467. Min Range: -4.7467
Max Act: 4.5592. Min Act: -0.1700
Data Index: 1139674 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7467. Min Range: -4.7467
Max Act: 4.5279. Min Act: -0.1700
Data Index: 8488434 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7467. Min Range: -4.7467
Max Act: 4.5279. Min Act: -0.1700
Data Index: 5465736 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7467. Min Range: -4.7467
Max Act: 4.5279. Min Act: -0.1700
Data Index: 1608815 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7467. Min Range: -4.7467
Max Act: 4.5279. Min Act: -0.1700
Data Index: 1102838 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7467. Min Range: -4.7467
Max Act: 4.4967. Min Act: -0.1700
Data Index: 3903604 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7467. Min Range: -4.7467
Max Act: 4.4967. Min Act: -0.1700
Data Index: 392301 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7467. Min Range: -4.7467
Max Act: 4.4654. Min Act: -0.1700
Data Index: 7465240 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7467. Min Range: -4.7467
Max Act: 4.4654. Min Act: -0.1700
Data Index: 7959444 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7467. Min Range: -4.7467
Max Act: 4.4654. Min Act: -0.1700
Data Index: 5886090 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7467. Min Range: -4.7467
Max Act: 4.4654. Min Act: -0.1700
Data Index: 3455313 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7467. Min Range: -4.7467
Max Act: 4.4654. Min Act: -0.1700
Data Index: 1462752 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7467. Min Range: -4.7467
Max Act: 4.4654. Min Act: -0.1700
Data Index: 1256068 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7467. Min Range: -4.7467
Max Act: 4.4967. Min Act: -0.1700
Data Index: 990106 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19