Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3213 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4290. Min Range: -6.4290
Max Act: 6.4290. Min Act: -0.1700
Data Index: 1227364 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4290. Min Range: -6.4290
Max Act: 6.3665. Min Act: -0.1700
Data Index: 6491052 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4290. Min Range: -6.4290
Max Act: 6.3353. Min Act: -0.1700
Data Index: 5047071 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4290. Min Range: -6.4290
Max Act: 6.2728. Min Act: -0.1700
Data Index: 7436547 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4290. Min Range: -6.4290
Max Act: 6.2728. Min Act: -0.1700
Data Index: 4968279 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4290. Min Range: -6.4290
Max Act: 6.3040. Min Act: -0.1700
Data Index: 5316044 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4290. Min Range: -6.4290
Max Act: 6.2103. Min Act: -0.1700
Data Index: 305634 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4290. Min Range: -6.4290
Max Act: 6.2103. Min Act: -0.1700
Data Index: 8572089 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4290. Min Range: -6.4290
Max Act: 6.1478. Min Act: -0.1700
Data Index: 7280185 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4290. Min Range: -6.4290
Max Act: 6.1478. Min Act: -0.1700
Data Index: 2047181 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4290. Min Range: -6.4290
Max Act: 6.1165. Min Act: -0.1700
Data Index: 3437208 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4290. Min Range: -6.4290
Max Act: 6.1165. Min Act: -0.1700
Data Index: 8492541 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4290. Min Range: -6.4290
Max Act: 6.0853. Min Act: -0.1700
Data Index: 2265064 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4290. Min Range: -6.4290
Max Act: 6.0853. Min Act: -0.1700
Data Index: 947737 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4290. Min Range: -6.4290
Max Act: 6.0540. Min Act: -0.1700
Data Index: 8265500 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4290. Min Range: -6.4290
Max Act: 6.0540. Min Act: -0.1700
Data Index: 3797868 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4290. Min Range: -6.4290
Max Act: 6.0540. Min Act: -0.1700
Data Index: 2699106 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4290. Min Range: -6.4290
Max Act: 6.0540. Min Act: -0.1700
Data Index: 3073851 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4290. Min Range: -6.4290
Max Act: 6.0228. Min Act: -0.1700
Data Index: 696316 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4290. Min Range: -6.4290
Max Act: 6.0540. Min Act: -0.1700
Data Index: 5900568 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19