Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 63 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4900. Min Range: -6.4900
Max Act: 6.4900. Min Act: -0.1700
Data Index: 8009656 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4900. Min Range: -6.4900
Max Act: 6.4900. Min Act: -0.1700
Data Index: 6637701 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4900. Min Range: -6.4900
Max Act: 6.3963. Min Act: -0.1700
Data Index: 5763252 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4900. Min Range: -6.4900
Max Act: 6.2088. Min Act: -0.1700
Data Index: 8091429 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4900. Min Range: -6.4900
Max Act: 6.0525. Min Act: -0.1700
Data Index: 593306 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4900. Min Range: -6.4900
Max Act: 6.0525. Min Act: -0.1700
Data Index: 9519 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4900. Min Range: -6.4900
Max Act: 6.0213. Min Act: -0.1700
Data Index: 2310323 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4900. Min Range: -6.4900
Max Act: 5.9900. Min Act: -0.1700
Data Index: 4676933 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4900. Min Range: -6.4900
Max Act: 5.9900. Min Act: -0.1700
Data Index: 4797976 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4900. Min Range: -6.4900
Max Act: 5.9588. Min Act: -0.1700
Data Index: 3376283 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4900. Min Range: -6.4900
Max Act: 5.9588. Min Act: -0.1700
Data Index: 7981304 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4900. Min Range: -6.4900
Max Act: 5.9588. Min Act: -0.1700
Data Index: 395822 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4900. Min Range: -6.4900
Max Act: 5.8963. Min Act: -0.1700
Data Index: 5135626 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4900. Min Range: -6.4900
Max Act: 5.9275. Min Act: -0.1700
Data Index: 6241036 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4900. Min Range: -6.4900
Max Act: 5.9275. Min Act: -0.1700
Data Index: 4001262 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4900. Min Range: -6.4900
Max Act: 5.9275. Min Act: -0.1700
Data Index: 2216237 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4900. Min Range: -6.4900
Max Act: 5.8650. Min Act: -0.1700
Data Index: 2276511 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4900. Min Range: -6.4900
Max Act: 5.8650. Min Act: -0.1700
Data Index: 3495177 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4900. Min Range: -6.4900
Max Act: 5.7713. Min Act: -0.1700
Data Index: 2175095 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4900. Min Range: -6.4900
Max Act: 5.7713. Min Act: -0.1700
Data Index: 2540778 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19