Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 756 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0599. Min Range: -4.0599
Max Act: 4.0599. Min Act: -0.1700
Data Index: 3947059 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0599. Min Range: -4.0599
Max Act: 3.9661. Min Act: -0.1700
Data Index: 5494062 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0599. Min Range: -4.0599
Max Act: 3.9661. Min Act: -0.1700
Data Index: 4061988 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0599. Min Range: -4.0599
Max Act: 3.9661. Min Act: -0.1700
Data Index: 5265665 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0599. Min Range: -4.0599
Max Act: 3.9036. Min Act: -0.1700
Data Index: 4081056 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0599. Min Range: -4.0599
Max Act: 3.9036. Min Act: -0.1700
Data Index: 3884811 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0599. Min Range: -4.0599
Max Act: 3.7159. Min Act: -0.1700
Data Index: 2439056 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0599. Min Range: -4.0599
Max Act: 3.5908. Min Act: -0.1700
Data Index: 7944977 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0599. Min Range: -4.0599
Max Act: 3.5125. Min Act: -0.1700
Data Index: 359098 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0599. Min Range: -4.0599
Max Act: 3.5595. Min Act: -0.1700
Data Index: 6986611 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0599. Min Range: -4.0599
Max Act: 3.5595. Min Act: -0.1700
Data Index: 6112977 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0599. Min Range: -4.0599
Max Act: 3.5595. Min Act: -0.1700
Data Index: 1382991 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0599. Min Range: -4.0599
Max Act: 3.5595. Min Act: -0.1700
Data Index: 5225957 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0599. Min Range: -4.0599
Max Act: 3.5908. Min Act: -0.1700
Data Index: 7145330 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0599. Min Range: -4.0599
Max Act: 3.5595. Min Act: -0.1700
Data Index: 1041657 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0599. Min Range: -4.0599
Max Act: 3.5595. Min Act: -0.1700
Data Index: 2133102 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0599. Min Range: -4.0599
Max Act: 3.5595. Min Act: -0.1700
Data Index: 2718308 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0599. Min Range: -4.0599
Max Act: 3.5438. Min Act: -0.1700
Data Index: 3892384 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0599. Min Range: -4.0599
Max Act: 3.5438. Min Act: -0.1700
Data Index: 5670254 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0599. Min Range: -4.0599
Max Act: 3.5281. Min Act: -0.1700
Data Index: 3304272 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19