Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2995 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2804. Min Range: -8.2804
Max Act: 8.2804. Min Act: -0.1700
Data Index: 8130327 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2804. Min Range: -8.2804
Max Act: 8.0304. Min Act: -0.1700
Data Index: 3728357 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2804. Min Range: -8.2804
Max Act: 7.7804. Min Act: -0.1700
Data Index: 8209523 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2804. Min Range: -8.2804
Max Act: 7.7179. Min Act: -0.1700
Data Index: 4306518 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2804. Min Range: -8.2804
Max Act: 7.7179. Min Act: -0.1700
Data Index: 4449689 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2804. Min Range: -8.2804
Max Act: 7.5929. Min Act: -0.1700
Data Index: 6211357 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2804. Min Range: -8.2804
Max Act: 7.5617. Min Act: -0.1700
Data Index: 6998184 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2804. Min Range: -8.2804
Max Act: 7.5617. Min Act: -0.1700
Data Index: 6976875 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2804. Min Range: -8.2804
Max Act: 7.4992. Min Act: -0.1700
Data Index: 4573992 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2804. Min Range: -8.2804
Max Act: 7.4367. Min Act: -0.1700
Data Index: 6003565 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2804. Min Range: -8.2804
Max Act: 7.4367. Min Act: -0.1700
Data Index: 2289376 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2804. Min Range: -8.2804
Max Act: 7.3742. Min Act: -0.1700
Data Index: 1096124 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2804. Min Range: -8.2804
Max Act: 7.4054. Min Act: -0.1700
Data Index: 6211354 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2804. Min Range: -8.2804
Max Act: 7.3429. Min Act: -0.1700
Data Index: 4034030 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2804. Min Range: -8.2804
Max Act: 7.3429. Min Act: -0.1700
Data Index: 3884793 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2804. Min Range: -8.2804
Max Act: 7.3429. Min Act: -0.1700
Data Index: 988187 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2804. Min Range: -8.2804
Max Act: 7.3117. Min Act: -0.1700
Data Index: 2069128 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2804. Min Range: -8.2804
Max Act: 7.2804. Min Act: -0.1700
Data Index: 7592031 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2804. Min Range: -8.2804
Max Act: 7.2492. Min Act: -0.1700
Data Index: 1191667 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2804. Min Range: -8.2804
Max Act: 7.2179. Min Act: -0.1700
Data Index: 3656286 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19