Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3314 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.5603. Min Act: -0.1700
Data Index: 5710218 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.1853. Min Act: -0.1700
Data Index: 1865814 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.1853. Min Act: -0.1700
Data Index: 5062664 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.0915. Min Act: -0.1700
Data Index: 5922260 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.0603. Min Act: -0.1700
Data Index: 6895606 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.0603. Min Act: -0.1700
Data Index: 2032382 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5603. Min Range: -6.5603
Max Act: 5.9978. Min Act: -0.1700
Data Index: 3247696 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.0290. Min Act: -0.1700
Data Index: 5889221 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.0290. Min Act: -0.1700
Data Index: 765315 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.0290. Min Act: -0.1700
Data Index: 4028819 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5603. Min Range: -6.5603
Max Act: 5.9665. Min Act: -0.1700
Data Index: 8051550 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5603. Min Range: -6.5603
Max Act: 5.9978. Min Act: -0.1700
Data Index: 2207489 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5603. Min Range: -6.5603
Max Act: 5.9353. Min Act: -0.1700
Data Index: 1787625 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5603. Min Range: -6.5603
Max Act: 5.9353. Min Act: -0.1700
Data Index: 581909 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5603. Min Range: -6.5603
Max Act: 5.9353. Min Act: -0.1700
Data Index: 3011896 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5603. Min Range: -6.5603
Max Act: 5.9040. Min Act: -0.1700
Data Index: 8530598 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5603. Min Range: -6.5603
Max Act: 5.9353. Min Act: -0.1700
Data Index: 2058608 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5603. Min Range: -6.5603
Max Act: 5.8728. Min Act: -0.1700
Data Index: 5525390 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5603. Min Range: -6.5603
Max Act: 5.8415. Min Act: -0.1700
Data Index: 5456086 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5603. Min Range: -6.5603
Max Act: 5.8728. Min Act: -0.1700
Data Index: 2278780 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19