Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3235 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1956. Min Range: -8.1956
Max Act: 8.1956. Min Act: -0.1700
Data Index: 4522079 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1956. Min Range: -8.1956
Max Act: 7.2581. Min Act: -0.1700
Data Index: 442874 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1956. Min Range: -8.1956
Max Act: 7.2269. Min Act: -0.1700
Data Index: 3205315 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1956. Min Range: -8.1956
Max Act: 7.2269. Min Act: -0.1700
Data Index: 2696237 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1956. Min Range: -8.1956
Max Act: 7.1331. Min Act: -0.1700
Data Index: 3761142 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1956. Min Range: -8.1956
Max Act: 7.1331. Min Act: -0.1700
Data Index: 1717837 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1956. Min Range: -8.1956
Max Act: 7.1019. Min Act: -0.1700
Data Index: 3123379 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1956. Min Range: -8.1956
Max Act: 7.0706. Min Act: -0.1700
Data Index: 180936 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1956. Min Range: -8.1956
Max Act: 6.9456. Min Act: -0.1700
Data Index: 3644343 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1956. Min Range: -8.1956
Max Act: 7.0081. Min Act: -0.1700
Data Index: 3277188 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1956. Min Range: -8.1956
Max Act: 7.0394. Min Act: -0.1700
Data Index: 8357223 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1956. Min Range: -8.1956
Max Act: 6.9769. Min Act: -0.1700
Data Index: 5201541 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1956. Min Range: -8.1956
Max Act: 6.9456. Min Act: -0.1700
Data Index: 2454138 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1956. Min Range: -8.1956
Max Act: 6.9769. Min Act: -0.1700
Data Index: 6238825 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1956. Min Range: -8.1956
Max Act: 6.9144. Min Act: -0.1700
Data Index: 1949531 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1956. Min Range: -8.1956
Max Act: 6.8831. Min Act: -0.1700
Data Index: 2198522 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1956. Min Range: -8.1956
Max Act: 6.9144. Min Act: -0.1700
Data Index: 7236007 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1956. Min Range: -8.1956
Max Act: 6.8831. Min Act: -0.1700
Data Index: 577873 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1956. Min Range: -8.1956
Max Act: 6.9144. Min Act: -0.1700
Data Index: 7323057 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1956. Min Range: -8.1956
Max Act: 6.8519. Min Act: -0.1700
Data Index: 1523253 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19