Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2620 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3136. Min Range: -5.3136
Max Act: 5.3136. Min Act: -0.1700
Data Index: 1523070 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3136. Min Range: -5.3136
Max Act: 5.0323. Min Act: -0.1700
Data Index: 4739786 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3136. Min Range: -5.3136
Max Act: 5.0011. Min Act: -0.1700
Data Index: 4871552 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3136. Min Range: -5.3136
Max Act: 5.0011. Min Act: -0.1700
Data Index: 4037986 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3136. Min Range: -5.3136
Max Act: 4.9386. Min Act: -0.1700
Data Index: 1938928 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3136. Min Range: -5.3136
Max Act: 4.9386. Min Act: -0.1700
Data Index: 7118275 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3136. Min Range: -5.3136
Max Act: 4.9073. Min Act: -0.1700
Data Index: 4005062 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3136. Min Range: -5.3136
Max Act: 4.8448. Min Act: -0.1700
Data Index: 7295246 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3136. Min Range: -5.3136
Max Act: 4.8761. Min Act: -0.1700
Data Index: 5609845 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3136. Min Range: -5.3136
Max Act: 4.8136. Min Act: -0.1700
Data Index: 907080 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3136. Min Range: -5.3136
Max Act: 4.8136. Min Act: -0.1700
Data Index: 4885951 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3136. Min Range: -5.3136
Max Act: 4.8136. Min Act: -0.1700
Data Index: 2302449 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3136. Min Range: -5.3136
Max Act: 4.7823. Min Act: -0.1700
Data Index: 5266990 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3136. Min Range: -5.3136
Max Act: 4.7823. Min Act: -0.1700
Data Index: 4372413 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3136. Min Range: -5.3136
Max Act: 4.7511. Min Act: -0.1700
Data Index: 2294575 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3136. Min Range: -5.3136
Max Act: 4.7511. Min Act: -0.1700
Data Index: 125308 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3136. Min Range: -5.3136
Max Act: 4.7511. Min Act: -0.1700
Data Index: 4005063 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3136. Min Range: -5.3136
Max Act: 4.7198. Min Act: -0.1700
Data Index: 649715 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3136. Min Range: -5.3136
Max Act: 4.7198. Min Act: -0.1700
Data Index: 1693454 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3136. Min Range: -5.3136
Max Act: 4.6886. Min Act: -0.1700
Data Index: 1922116 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19