Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4610 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9710. Min Range: -6.9710
Max Act: 6.9710. Min Act: -0.1700
Data Index: 4929292 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9710. Min Range: -6.9710
Max Act: 6.8147. Min Act: -0.1700
Data Index: 5888957 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9710. Min Range: -6.9710
Max Act: 6.7835. Min Act: -0.1700
Data Index: 6685131 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9710. Min Range: -6.9710
Max Act: 6.7835. Min Act: -0.1700
Data Index: 179588 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9710. Min Range: -6.9710
Max Act: 6.7210. Min Act: -0.1700
Data Index: 1800455 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9710. Min Range: -6.9710
Max Act: 6.7210. Min Act: -0.1700
Data Index: 2058735 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9710. Min Range: -6.9710
Max Act: 6.6897. Min Act: -0.1700
Data Index: 4254139 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9710. Min Range: -6.9710
Max Act: 6.6897. Min Act: -0.1700
Data Index: 7942896 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9710. Min Range: -6.9710
Max Act: 6.6897. Min Act: -0.1700
Data Index: 8770204 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9710. Min Range: -6.9710
Max Act: 6.6585. Min Act: -0.1700
Data Index: 1160998 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9710. Min Range: -6.9710
Max Act: 6.6897. Min Act: -0.1700
Data Index: 733238 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9710. Min Range: -6.9710
Max Act: 6.6272. Min Act: -0.1700
Data Index: 774238 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9710. Min Range: -6.9710
Max Act: 6.6272. Min Act: -0.1700
Data Index: 2127249 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9710. Min Range: -6.9710
Max Act: 6.6272. Min Act: -0.1700
Data Index: 8795092 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9710. Min Range: -6.9710
Max Act: 6.5335. Min Act: -0.1700
Data Index: 920071 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9710. Min Range: -6.9710
Max Act: 6.5335. Min Act: -0.1700
Data Index: 6877378 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9710. Min Range: -6.9710
Max Act: 6.5335. Min Act: -0.1700
Data Index: 3264704 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9710. Min Range: -6.9710
Max Act: 6.5335. Min Act: -0.1700
Data Index: 8377783 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9710. Min Range: -6.9710
Max Act: 6.5335. Min Act: -0.1700
Data Index: 1181369 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9710. Min Range: -6.9710
Max Act: 6.5335. Min Act: -0.1700
Data Index: 3315815 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19