Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3833 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1764. Min Range: -6.1764
Max Act: 6.1764. Min Act: -0.1700
Data Index: 3160532 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1764. Min Range: -6.1764
Max Act: 6.1139. Min Act: -0.1700
Data Index: 4198367 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1764. Min Range: -6.1764
Max Act: 6.0202. Min Act: -0.1700
Data Index: 2015306 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1764. Min Range: -6.1764
Max Act: 5.8952. Min Act: -0.1700
Data Index: 2623347 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1764. Min Range: -6.1764
Max Act: 5.8952. Min Act: -0.1700
Data Index: 641999 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1764. Min Range: -6.1764
Max Act: 5.8952. Min Act: -0.1700
Data Index: 7283930 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1764. Min Range: -6.1764
Max Act: 5.8952. Min Act: -0.1700
Data Index: 3095050 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1764. Min Range: -6.1764
Max Act: 5.9264. Min Act: -0.1700
Data Index: 7395027 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1764. Min Range: -6.1764
Max Act: 5.8952. Min Act: -0.1700
Data Index: 3136485 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1764. Min Range: -6.1764
Max Act: 5.8014. Min Act: -0.1700
Data Index: 6512630 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1764. Min Range: -6.1764
Max Act: 5.8327. Min Act: -0.1700
Data Index: 1239285 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1764. Min Range: -6.1764
Max Act: 5.8327. Min Act: -0.1700
Data Index: 6688850 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1764. Min Range: -6.1764
Max Act: 5.8327. Min Act: -0.1700
Data Index: 7511419 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1764. Min Range: -6.1764
Max Act: 5.8014. Min Act: -0.1700
Data Index: 7133516 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1764. Min Range: -6.1764
Max Act: 5.8014. Min Act: -0.1700
Data Index: 942928 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1764. Min Range: -6.1764
Max Act: 5.8014. Min Act: -0.1700
Data Index: 3100741 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1764. Min Range: -6.1764
Max Act: 5.8014. Min Act: -0.1700
Data Index: 3566125 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1764. Min Range: -6.1764
Max Act: 5.7389. Min Act: -0.1700
Data Index: 3853424 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1764. Min Range: -6.1764
Max Act: 5.7702. Min Act: -0.1700
Data Index: 5410955 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1764. Min Range: -6.1764
Max Act: 5.7077. Min Act: -0.1700
Data Index: 1793071 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19