Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3977 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1720. Min Range: -6.1720
Max Act: 6.1720. Min Act: -0.1700
Data Index: 51153 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.8595. Min Act: -0.1700
Data Index: 6138075 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.8282. Min Act: -0.1700
Data Index: 8145294 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.8282. Min Act: -0.1700
Data Index: 2035788 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.7970. Min Act: -0.1700
Data Index: 8077113 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.7657. Min Act: -0.1700
Data Index: 7065023 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.7657. Min Act: -0.1700
Data Index: 6947849 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.7032. Min Act: -0.1700
Data Index: 907963 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.6720. Min Act: -0.1700
Data Index: 5038234 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.6407. Min Act: -0.1700
Data Index: 5806680 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.6095. Min Act: -0.1700
Data Index: 2643595 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.5470. Min Act: -0.1700
Data Index: 6251607 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.5470. Min Act: -0.1700
Data Index: 777584 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.5157. Min Act: -0.1700
Data Index: 7889423 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.5470. Min Act: -0.1700
Data Index: 2599225 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.4845. Min Act: -0.1700
Data Index: 2698792 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.5157. Min Act: -0.1700
Data Index: 6056391 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.5157. Min Act: -0.1700
Data Index: 3425619 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.4845. Min Act: -0.1700
Data Index: 2408542 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.4532. Min Act: -0.1700
Data Index: 1279477 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19