Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4378 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3669. Min Range: -5.3669
Max Act: 5.3669. Min Act: -0.1700
Data Index: 4995649 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3669. Min Range: -5.3669
Max Act: 5.2732. Min Act: -0.1700
Data Index: 2661284 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3669. Min Range: -5.3669
Max Act: 5.2732. Min Act: -0.1700
Data Index: 7442135 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3669. Min Range: -5.3669
Max Act: 5.2732. Min Act: -0.1699
Data Index: 5615096 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3669. Min Range: -5.3669
Max Act: 5.2107. Min Act: -0.1700
Data Index: 1740127 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3669. Min Range: -5.3669
Max Act: 5.1794. Min Act: -0.1700
Data Index: 7716518 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3669. Min Range: -5.3669
Max Act: 5.2107. Min Act: -0.1700
Data Index: 1740129 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3669. Min Range: -5.3669
Max Act: 5.1169. Min Act: -0.1700
Data Index: 1740134 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3669. Min Range: -5.3669
Max Act: 5.0857. Min Act: -0.1700
Data Index: 3719260 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3669. Min Range: -5.3669
Max Act: 5.1169. Min Act: -0.1700
Data Index: 1422090 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3669. Min Range: -5.3669
Max Act: 5.0857. Min Act: -0.1700
Data Index: 1740132 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3669. Min Range: -5.3669
Max Act: 5.0857. Min Act: -0.1700
Data Index: 3274959 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3669. Min Range: -5.3669
Max Act: 5.0544. Min Act: -0.1700
Data Index: 3427885 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3669. Min Range: -5.3669
Max Act: 5.0857. Min Act: -0.1700
Data Index: 4621172 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3669. Min Range: -5.3669
Max Act: 5.0544. Min Act: -0.1700
Data Index: 6661857 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3669. Min Range: -5.3669
Max Act: 5.0232. Min Act: -0.1700
Data Index: 7317114 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3669. Min Range: -5.3669
Max Act: 4.9607. Min Act: -0.1700
Data Index: 1191540 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3669. Min Range: -5.3669
Max Act: 4.9607. Min Act: -0.1700
Data Index: 524323 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3669. Min Range: -5.3669
Max Act: 4.9919. Min Act: -0.1700
Data Index: 4067987 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3669. Min Range: -5.3669
Max Act: 4.9919. Min Act: -0.1700
Data Index: 1364112 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19