Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3460 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0453. Min Range: -6.0453
Max Act: 6.0453. Min Act: -0.1700
Data Index: 3821194 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0453. Min Range: -6.0453
Max Act: 6.0140. Min Act: -0.1700
Data Index: 1347991 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0453. Min Range: -6.0453
Max Act: 5.8578. Min Act: -0.1700
Data Index: 4985608 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0453. Min Range: -6.0453
Max Act: 5.8890. Min Act: -0.1700
Data Index: 4896766 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0453. Min Range: -6.0453
Max Act: 5.8578. Min Act: -0.1700
Data Index: 6755964 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0453. Min Range: -6.0453
Max Act: 5.8578. Min Act: -0.1700
Data Index: 1019024 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0453. Min Range: -6.0453
Max Act: 5.8265. Min Act: -0.1700
Data Index: 5820770 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0453. Min Range: -6.0453
Max Act: 5.8265. Min Act: -0.1700
Data Index: 1347992 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0453. Min Range: -6.0453
Max Act: 5.8265. Min Act: -0.1700
Data Index: 971395 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0453. Min Range: -6.0453
Max Act: 5.7953. Min Act: -0.1700
Data Index: 1716419 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0453. Min Range: -6.0453
Max Act: 5.7328. Min Act: -0.1700
Data Index: 4528610 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0453. Min Range: -6.0453
Max Act: 5.7328. Min Act: -0.1700
Data Index: 2913192 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0453. Min Range: -6.0453
Max Act: 5.7328. Min Act: -0.1700
Data Index: 971394 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0453. Min Range: -6.0453
Max Act: 5.6703. Min Act: -0.1700
Data Index: 2467248 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0453. Min Range: -6.0453
Max Act: 5.6703. Min Act: -0.1700
Data Index: 6798201 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0453. Min Range: -6.0453
Max Act: 5.6390. Min Act: -0.1700
Data Index: 6691074 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0453. Min Range: -6.0453
Max Act: 5.6078. Min Act: -0.1700
Data Index: 954832 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0453. Min Range: -6.0453
Max Act: 5.6078. Min Act: -0.1700
Data Index: 7957840 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0453. Min Range: -6.0453
Max Act: 5.6078. Min Act: -0.1700
Data Index: 1347994 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0453. Min Range: -6.0453
Max Act: 5.6078. Min Act: -0.1700
Data Index: 52975 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19