Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4087 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7577. Min Range: -5.7577
Max Act: 5.7577. Min Act: -0.1700
Data Index: 8339623 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7577. Min Range: -5.7577
Max Act: 5.7265. Min Act: -0.1700
Data Index: 4146093 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7577. Min Range: -5.7577
Max Act: 5.6952. Min Act: -0.1700
Data Index: 2969147 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7577. Min Range: -5.7577
Max Act: 5.7265. Min Act: -0.1700
Data Index: 6167781 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7577. Min Range: -5.7577
Max Act: 5.6952. Min Act: -0.1700
Data Index: 3912873 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7577. Min Range: -5.7577
Max Act: 5.6952. Min Act: -0.1700
Data Index: 7384026 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7577. Min Range: -5.7577
Max Act: 5.6952. Min Act: -0.1700
Data Index: 8213288 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7577. Min Range: -5.7577
Max Act: 5.6327. Min Act: -0.1700
Data Index: 5408671 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7577. Min Range: -5.7577
Max Act: 5.6327. Min Act: -0.1700
Data Index: 5853176 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7577. Min Range: -5.7577
Max Act: 5.6640. Min Act: -0.1700
Data Index: 8159444 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7577. Min Range: -5.7577
Max Act: 5.6015. Min Act: -0.1700
Data Index: 740725 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7577. Min Range: -5.7577
Max Act: 5.6015. Min Act: -0.1700
Data Index: 8541957 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7577. Min Range: -5.7577
Max Act: 5.5702. Min Act: -0.1700
Data Index: 8514292 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7577. Min Range: -5.7577
Max Act: 5.6015. Min Act: -0.1700
Data Index: 3349100 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7577. Min Range: -5.7577
Max Act: 5.6015. Min Act: -0.1700
Data Index: 5297257 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7577. Min Range: -5.7577
Max Act: 5.6015. Min Act: -0.1700
Data Index: 2219646 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7577. Min Range: -5.7577
Max Act: 5.6015. Min Act: -0.1700
Data Index: 7619297 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7577. Min Range: -5.7577
Max Act: 5.5702. Min Act: -0.1700
Data Index: 3091222 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7577. Min Range: -5.7577
Max Act: 5.6015. Min Act: -0.1700
Data Index: 2935487 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7577. Min Range: -5.7577
Max Act: 5.6015. Min Act: -0.1700
Data Index: 191594 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19