Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3330 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2413. Min Range: -7.2413
Max Act: 7.2413. Min Act: -0.1700
Data Index: 3655183 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2413. Min Range: -7.2413
Max Act: 7.0851. Min Act: -0.1700
Data Index: 5120092 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2413. Min Range: -7.2413
Max Act: 6.9601. Min Act: -0.1700
Data Index: 8542093 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2413. Min Range: -7.2413
Max Act: 6.9913. Min Act: -0.1700
Data Index: 2754281 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2413. Min Range: -7.2413
Max Act: 6.9601. Min Act: -0.1700
Data Index: 4059332 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2413. Min Range: -7.2413
Max Act: 6.9288. Min Act: -0.1700
Data Index: 6807337 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2413. Min Range: -7.2413
Max Act: 6.9288. Min Act: -0.1700
Data Index: 1312451 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2413. Min Range: -7.2413
Max Act: 6.9288. Min Act: -0.1700
Data Index: 5903160 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2413. Min Range: -7.2413
Max Act: 6.8663. Min Act: -0.1700
Data Index: 8542180 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2413. Min Range: -7.2413
Max Act: 6.8663. Min Act: -0.1700
Data Index: 895967 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2413. Min Range: -7.2413
Max Act: 6.8351. Min Act: -0.1700
Data Index: 4831533 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2413. Min Range: -7.2413
Max Act: 6.8038. Min Act: -0.1700
Data Index: 6929078 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2413. Min Range: -7.2413
Max Act: 6.8038. Min Act: -0.1700
Data Index: 6121570 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2413. Min Range: -7.2413
Max Act: 6.8038. Min Act: -0.1700
Data Index: 2190955 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2413. Min Range: -7.2413
Max Act: 6.8351. Min Act: -0.1700
Data Index: 3993277 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2413. Min Range: -7.2413
Max Act: 6.7726. Min Act: -0.1700
Data Index: 7273146 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2413. Min Range: -7.2413
Max Act: 6.7726. Min Act: -0.1700
Data Index: 7688292 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2413. Min Range: -7.2413
Max Act: 6.7726. Min Act: -0.1700
Data Index: 6350049 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2413. Min Range: -7.2413
Max Act: 6.7726. Min Act: -0.1700
Data Index: 4891308 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2413. Min Range: -7.2413
Max Act: 6.7413. Min Act: -0.1700
Data Index: 3011830 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19