Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2163 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0038. Min Range: -6.0038
Max Act: 6.0038. Min Act: -0.1700
Data Index: 5572964 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0038. Min Range: -6.0038
Max Act: 5.7850. Min Act: -0.1700
Data Index: 1881840 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0038. Min Range: -6.0038
Max Act: 5.7225. Min Act: -0.1700
Data Index: 2567280 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0038. Min Range: -6.0038
Max Act: 5.6288. Min Act: -0.1700
Data Index: 2707945 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0038. Min Range: -6.0038
Max Act: 5.6288. Min Act: -0.1700
Data Index: 4969680 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0038. Min Range: -6.0038
Max Act: 5.6288. Min Act: -0.1700
Data Index: 3378612 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0038. Min Range: -6.0038
Max Act: 5.5350. Min Act: -0.1700
Data Index: 8378118 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0038. Min Range: -6.0038
Max Act: 5.5975. Min Act: -0.1700
Data Index: 6974610 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0038. Min Range: -6.0038
Max Act: 5.5350. Min Act: -0.1700
Data Index: 893812 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0038. Min Range: -6.0038
Max Act: 5.5663. Min Act: -0.1700
Data Index: 1936189 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0038. Min Range: -6.0038
Max Act: 5.5350. Min Act: -0.1700
Data Index: 8526071 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0038. Min Range: -6.0038
Max Act: 5.5663. Min Act: -0.1700
Data Index: 6168278 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0038. Min Range: -6.0038
Max Act: 5.5663. Min Act: -0.1700
Data Index: 1096771 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0038. Min Range: -6.0038
Max Act: 5.5350. Min Act: -0.1700
Data Index: 4162279 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0038. Min Range: -6.0038
Max Act: 5.5038. Min Act: -0.1700
Data Index: 3278947 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0038. Min Range: -6.0038
Max Act: 5.5350. Min Act: -0.1700
Data Index: 3214749 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0038. Min Range: -6.0038
Max Act: 5.5038. Min Act: -0.1700
Data Index: 6418411 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0038. Min Range: -6.0038
Max Act: 5.4725. Min Act: -0.1700
Data Index: 54300 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0038. Min Range: -6.0038
Max Act: 5.5350. Min Act: -0.1700
Data Index: 7633890 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0038. Min Range: -6.0038
Max Act: 5.5038. Min Act: -0.1700
Data Index: 202701 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19