Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3083 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8407. Min Range: -2.8407
Max Act: 2.8407. Min Act: -0.1700
Data Index: 4081442 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8407. Min Range: -2.8407
Max Act: 2.7451. Min Act: -0.1700
Data Index: 602984 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8407. Min Range: -2.8407
Max Act: 2.7451. Min Act: -0.1700
Data Index: 4890525 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8407. Min Range: -2.8407
Max Act: 2.7291. Min Act: -0.1700
Data Index: 181917 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8407. Min Range: -2.8407
Max Act: 2.7131. Min Act: -0.1700
Data Index: 4764164 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8407. Min Range: -2.8407
Max Act: 2.6811. Min Act: -0.1700
Data Index: 6205123 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8407. Min Range: -2.8407
Max Act: 2.6651. Min Act: -0.1700
Data Index: 2763078 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8407. Min Range: -2.8407
Max Act: 2.6490. Min Act: -0.1700
Data Index: 3867345 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8407. Min Range: -2.8407
Max Act: 2.6330. Min Act: -0.1700
Data Index: 4089004 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8407. Min Range: -2.8407
Max Act: 2.6008. Min Act: -0.1700
Data Index: 8655152 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8407. Min Range: -2.8407
Max Act: 2.6330. Min Act: -0.1700
Data Index: 6482432 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8407. Min Range: -2.8407
Max Act: 2.6008. Min Act: -0.1700
Data Index: 5570110 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8407. Min Range: -2.8407
Max Act: 2.6008. Min Act: -0.1700
Data Index: 1273795 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8407. Min Range: -2.8407
Max Act: 2.6008. Min Act: -0.1700
Data Index: 421972 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8407. Min Range: -2.8407
Max Act: 2.6008. Min Act: -0.1700
Data Index: 7478781 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8407. Min Range: -2.8407
Max Act: 2.5686. Min Act: -0.1700
Data Index: 1121594 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8407. Min Range: -2.8407
Max Act: 2.5525. Min Act: -0.1700
Data Index: 4062048 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8407. Min Range: -2.8407
Max Act: 2.5525. Min Act: -0.1700
Data Index: 2443543 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8407. Min Range: -2.8407
Max Act: 2.5363. Min Act: -0.1700
Data Index: 2775608 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8407. Min Range: -2.8407
Max Act: 2.5363. Min Act: -0.1700
Data Index: 2121009 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19