Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1759 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7078. Min Range: -9.7078
Max Act: 9.7078. Min Act: -0.1700
Data Index: 8024490 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7078. Min Range: -9.7078
Max Act: 9.5828. Min Act: -0.1700
Data Index: 3033763 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7078. Min Range: -9.7078
Max Act: 9.3953. Min Act: -0.1700
Data Index: 1645390 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7078. Min Range: -9.7078
Max Act: 9.3328. Min Act: -0.1700
Data Index: 2152685 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7078. Min Range: -9.7078
Max Act: 9.3328. Min Act: -0.1700
Data Index: 500168 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7078. Min Range: -9.7078
Max Act: 9.2703. Min Act: -0.1700
Data Index: 3716312 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7078. Min Range: -9.7078
Max Act: 9.2703. Min Act: -0.1700
Data Index: 4585502 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7078. Min Range: -9.7078
Max Act: 9.2078. Min Act: -0.1700
Data Index: 7031849 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7078. Min Range: -9.7078
Max Act: 9.1453. Min Act: -0.1700
Data Index: 6328390 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7078. Min Range: -9.7078
Max Act: 9.0203. Min Act: -0.1700
Data Index: 4247102 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7078. Min Range: -9.7078
Max Act: 9.0203. Min Act: -0.1700
Data Index: 2445591 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7078. Min Range: -9.7078
Max Act: 8.9578. Min Act: -0.1700
Data Index: 8300399 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7078. Min Range: -9.7078
Max Act: 9.0203. Min Act: -0.1700
Data Index: 7946168 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7078. Min Range: -9.7078
Max Act: 8.9578. Min Act: -0.1700
Data Index: 342064 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7078. Min Range: -9.7078
Max Act: 8.9578. Min Act: -0.1700
Data Index: 4236010 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7078. Min Range: -9.7078
Max Act: 8.8953. Min Act: -0.1700
Data Index: 2503493 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7078. Min Range: -9.7078
Max Act: 8.8953. Min Act: -0.1700
Data Index: 2154453 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7078. Min Range: -9.7078
Max Act: 8.8953. Min Act: -0.1700
Data Index: 3610719 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7078. Min Range: -9.7078
Max Act: 8.8328. Min Act: -0.1700
Data Index: 4889482 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7078. Min Range: -9.7078
Max Act: 8.8328. Min Act: -0.1700
Data Index: 1196285 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19