Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3138 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.5546. Min Act: -0.1700
Data Index: 5776616 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.4609. Min Act: -0.1700
Data Index: 6587400 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.3984. Min Act: -0.1700
Data Index: 3181958 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.4296. Min Act: -0.1700
Data Index: 6111905 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.3984. Min Act: -0.1700
Data Index: 2329035 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.4296. Min Act: -0.1700
Data Index: 2363832 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.3984. Min Act: -0.1700
Data Index: 2487192 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.3359. Min Act: -0.1700
Data Index: 1517863 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.3671. Min Act: -0.1700
Data Index: 4822528 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.3359. Min Act: -0.1700
Data Index: 1940153 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.3359. Min Act: -0.1700
Data Index: 2987656 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.3046. Min Act: -0.1700
Data Index: 799665 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.3046. Min Act: -0.1700
Data Index: 1517861 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.3359. Min Act: -0.1700
Data Index: 7069144 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.3046. Min Act: -0.1700
Data Index: 5226343 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.3046. Min Act: -0.1700
Data Index: 6719098 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.2734. Min Act: -0.1700
Data Index: 7461278 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.2734. Min Act: -0.1700
Data Index: 3486349 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.2734. Min Act: -0.1700
Data Index: 2235032 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.2734. Min Act: -0.1700
Data Index: 3771007 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19