Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3180 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0889. Min Range: -7.0889
Max Act: 7.0889. Min Act: -0.1700
Data Index: 7907981 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0889. Min Range: -7.0889
Max Act: 6.6826. Min Act: -0.1700
Data Index: 5770641 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0889. Min Range: -7.0889
Max Act: 6.3701. Min Act: -0.1700
Data Index: 2848201 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0889. Min Range: -7.0889
Max Act: 6.2451. Min Act: -0.1700
Data Index: 7329562 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0889. Min Range: -7.0889
Max Act: 6.2139. Min Act: -0.1700
Data Index: 6145034 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0889. Min Range: -7.0889
Max Act: 6.1201. Min Act: -0.1700
Data Index: 1259944 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0889. Min Range: -7.0889
Max Act: 6.1514. Min Act: -0.1700
Data Index: 6133581 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0889. Min Range: -7.0889
Max Act: 6.1201. Min Act: -0.1700
Data Index: 7904433 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0889. Min Range: -7.0889
Max Act: 6.1201. Min Act: -0.1700
Data Index: 674315 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0889. Min Range: -7.0889
Max Act: 6.1201. Min Act: -0.1700
Data Index: 8498412 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0889. Min Range: -7.0889
Max Act: 6.0576. Min Act: -0.1700
Data Index: 7596211 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0889. Min Range: -7.0889
Max Act: 5.9951. Min Act: -0.1700
Data Index: 7711959 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0889. Min Range: -7.0889
Max Act: 5.9951. Min Act: -0.1700
Data Index: 4082600 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0889. Min Range: -7.0889
Max Act: 5.9951. Min Act: -0.1700
Data Index: 4749124 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0889. Min Range: -7.0889
Max Act: 5.9639. Min Act: -0.1700
Data Index: 8238574 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0889. Min Range: -7.0889
Max Act: 5.9639. Min Act: -0.1700
Data Index: 5062259 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0889. Min Range: -7.0889
Max Act: 5.9014. Min Act: -0.1700
Data Index: 466881 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0889. Min Range: -7.0889
Max Act: 5.9326. Min Act: -0.1700
Data Index: 7054317 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0889. Min Range: -7.0889
Max Act: 5.9639. Min Act: -0.1700
Data Index: 1872127 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0889. Min Range: -7.0889
Max Act: 5.9014. Min Act: -0.1700
Data Index: 8825625 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19