Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5864 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.2424. Min Act: -0.1700
Data Index: 7030567 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.1174. Min Act: -0.1700
Data Index: 4978783 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.0862. Min Act: -0.1700
Data Index: 7398826 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.0862. Min Act: -0.1700
Data Index: 7863379 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.0549. Min Act: -0.1700
Data Index: 4653614 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.0862. Min Act: -0.1700
Data Index: 1102598 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.0549. Min Act: -0.1700
Data Index: 4617188 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2424. Min Range: -6.2424
Max Act: 5.9924. Min Act: -0.1700
Data Index: 6161848 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2424. Min Range: -6.2424
Max Act: 5.9924. Min Act: -0.1700
Data Index: 7729997 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2424. Min Range: -6.2424
Max Act: 5.9612. Min Act: -0.1700
Data Index: 4606609 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2424. Min Range: -6.2424
Max Act: 5.9612. Min Act: -0.1700
Data Index: 161023 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2424. Min Range: -6.2424
Max Act: 5.9612. Min Act: -0.1700
Data Index: 6810534 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2424. Min Range: -6.2424
Max Act: 5.9612. Min Act: -0.1700
Data Index: 1561008 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2424. Min Range: -6.2424
Max Act: 5.9612. Min Act: -0.1700
Data Index: 7140021 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2424. Min Range: -6.2424
Max Act: 5.9612. Min Act: -0.1700
Data Index: 3899630 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2424. Min Range: -6.2424
Max Act: 5.9612. Min Act: -0.1700
Data Index: 6747979 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2424. Min Range: -6.2424
Max Act: 5.9612. Min Act: -0.1700
Data Index: 4237210 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2424. Min Range: -6.2424
Max Act: 5.8987. Min Act: -0.1700
Data Index: 2161937 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2424. Min Range: -6.2424
Max Act: 5.8987. Min Act: -0.1700
Data Index: 6661117 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2424. Min Range: -6.2424
Max Act: 5.9299. Min Act: -0.1700
Data Index: 4911478 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19