Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8975. Min Range: -5.8975
Max Act: 5.8975. Min Act: -0.1700
Data Index: 6516945 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8975. Min Range: -5.8975
Max Act: 5.7413. Min Act: -0.1700
Data Index: 8795936 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8975. Min Range: -5.8975
Max Act: 5.7413. Min Act: -0.1700
Data Index: 8382334 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8975. Min Range: -5.8975
Max Act: 5.5225. Min Act: -0.1700
Data Index: 6669383 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8975. Min Range: -5.8975
Max Act: 5.3975. Min Act: -0.1700
Data Index: 8126608 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8975. Min Range: -5.8975
Max Act: 5.4288. Min Act: -0.1700
Data Index: 5817740 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8975. Min Range: -5.8975
Max Act: 5.3975. Min Act: -0.1700
Data Index: 2877622 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8975. Min Range: -5.8975
Max Act: 5.3350. Min Act: -0.1700
Data Index: 8658832 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8975. Min Range: -5.8975
Max Act: 5.3038. Min Act: -0.1700
Data Index: 3325783 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8975. Min Range: -5.8975
Max Act: 5.2413. Min Act: -0.1700
Data Index: 20102 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8975. Min Range: -5.8975
Max Act: 5.2100. Min Act: -0.1700
Data Index: 4027078 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8975. Min Range: -5.8975
Max Act: 5.1788. Min Act: -0.1700
Data Index: 7283064 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8975. Min Range: -5.8975
Max Act: 5.1475. Min Act: -0.1700
Data Index: 2915406 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8975. Min Range: -5.8975
Max Act: 5.1788. Min Act: -0.1700
Data Index: 2980468 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8975. Min Range: -5.8975
Max Act: 5.1788. Min Act: -0.1700
Data Index: 6809338 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8975. Min Range: -5.8975
Max Act: 5.1475. Min Act: -0.1700
Data Index: 809762 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8975. Min Range: -5.8975
Max Act: 5.1163. Min Act: -0.1700
Data Index: 746296 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8975. Min Range: -5.8975
Max Act: 5.1163. Min Act: -0.1700
Data Index: 8192184 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8975. Min Range: -5.8975
Max Act: 5.0538. Min Act: -0.1700
Data Index: 453422 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8975. Min Range: -5.8975
Max Act: 5.0850. Min Act: -0.1700
Data Index: 7339093 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19