Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1172 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3968. Min Range: -8.3968
Max Act: 8.3968. Min Act: -0.1700
Data Index: 5341516 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3968. Min Range: -8.3968
Max Act: 8.1468. Min Act: -0.1700
Data Index: 6739172 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3968. Min Range: -8.3968
Max Act: 7.8968. Min Act: -0.1700
Data Index: 7316059 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3968. Min Range: -8.3968
Max Act: 7.8030. Min Act: -0.1700
Data Index: 7061793 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3968. Min Range: -8.3968
Max Act: 7.8343. Min Act: -0.1700
Data Index: 8812437 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3968. Min Range: -8.3968
Max Act: 7.8030. Min Act: -0.1700
Data Index: 3115991 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3968. Min Range: -8.3968
Max Act: 7.7405. Min Act: -0.1700
Data Index: 8791065 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3968. Min Range: -8.3968
Max Act: 7.7718. Min Act: -0.1700
Data Index: 3389370 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3968. Min Range: -8.3968
Max Act: 7.7718. Min Act: -0.1700
Data Index: 6848121 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3968. Min Range: -8.3968
Max Act: 7.7718. Min Act: -0.1700
Data Index: 787402 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3968. Min Range: -8.3968
Max Act: 7.7093. Min Act: -0.1700
Data Index: 1921998 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3968. Min Range: -8.3968
Max Act: 7.6780. Min Act: -0.1700
Data Index: 7427888 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3968. Min Range: -8.3968
Max Act: 7.6155. Min Act: -0.1700
Data Index: 4010423 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3968. Min Range: -8.3968
Max Act: 7.6155. Min Act: -0.1700
Data Index: 5472886 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3968. Min Range: -8.3968
Max Act: 7.6468. Min Act: -0.1700
Data Index: 6715643 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3968. Min Range: -8.3968
Max Act: 7.6155. Min Act: -0.1700
Data Index: 495061 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3968. Min Range: -8.3968
Max Act: 7.6468. Min Act: -0.1700
Data Index: 2312006 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3968. Min Range: -8.3968
Max Act: 7.6155. Min Act: -0.1700
Data Index: 3229690 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3968. Min Range: -8.3968
Max Act: 7.5843. Min Act: -0.1700
Data Index: 1937426 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3968. Min Range: -8.3968
Max Act: 7.5843. Min Act: -0.1700
Data Index: 7434121 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19