Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2466 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9076. Min Range: -5.9076
Max Act: 5.9076. Min Act: -0.1700
Data Index: 6488373 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9076. Min Range: -5.9076
Max Act: 5.6888. Min Act: -0.1700
Data Index: 1807180 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9076. Min Range: -5.9076
Max Act: 5.5013. Min Act: -0.1700
Data Index: 8497861 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9076. Min Range: -5.9076
Max Act: 5.4701. Min Act: -0.1700
Data Index: 3790546 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9076. Min Range: -5.9076
Max Act: 5.4388. Min Act: -0.1700
Data Index: 3035376 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9076. Min Range: -5.9076
Max Act: 5.3763. Min Act: -0.1700
Data Index: 3972126 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9076. Min Range: -5.9076
Max Act: 5.3451. Min Act: -0.1700
Data Index: 5499053 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9076. Min Range: -5.9076
Max Act: 5.3138. Min Act: -0.1700
Data Index: 8312903 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9076. Min Range: -5.9076
Max Act: 5.2826. Min Act: -0.1700
Data Index: 7127790 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9076. Min Range: -5.9076
Max Act: 5.2826. Min Act: -0.1700
Data Index: 8556009 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9076. Min Range: -5.9076
Max Act: 5.3138. Min Act: -0.1700
Data Index: 7240198 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9076. Min Range: -5.9076
Max Act: 5.2513. Min Act: -0.1700
Data Index: 5927481 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9076. Min Range: -5.9076
Max Act: 5.1888. Min Act: -0.1700
Data Index: 2524920 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9076. Min Range: -5.9076
Max Act: 5.1888. Min Act: -0.1700
Data Index: 4455800 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9076. Min Range: -5.9076
Max Act: 5.1888. Min Act: -0.1700
Data Index: 7365832 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9076. Min Range: -5.9076
Max Act: 5.2201. Min Act: -0.1700
Data Index: 8179855 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9076. Min Range: -5.9076
Max Act: 5.2201. Min Act: -0.1700
Data Index: 867118 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9076. Min Range: -5.9076
Max Act: 5.1888. Min Act: -0.1700
Data Index: 671198 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9076. Min Range: -5.9076
Max Act: 5.1888. Min Act: -0.1700
Data Index: 6114557 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9076. Min Range: -5.9076
Max Act: 5.1576. Min Act: -0.1700
Data Index: 5236083 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19