Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 30 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4640. Min Range: -1.4640
Max Act: 1.4640. Min Act: -0.1700
Data Index: 4260581 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4640. Min Range: -1.4640
Max Act: 1.4200. Min Act: -0.1700
Data Index: 8145347 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4640. Min Range: -1.4640
Max Act: 1.4376. Min Act: -0.1700
Data Index: 3476767 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4640. Min Range: -1.4640
Max Act: 1.4376. Min Act: -0.1700
Data Index: 2023689 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4640. Min Range: -1.4640
Max Act: 1.4112. Min Act: -0.1700
Data Index: 7480887 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4640. Min Range: -1.4640
Max Act: 1.4112. Min Act: -0.1700
Data Index: 4123340 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4640. Min Range: -1.4640
Max Act: 1.4112. Min Act: -0.1700
Data Index: 1267017 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4640. Min Range: -1.4640
Max Act: 1.4112. Min Act: -0.1700
Data Index: 8726426 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4640. Min Range: -1.4640
Max Act: 1.4024. Min Act: -0.1700
Data Index: 508715 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4640. Min Range: -1.4640
Max Act: 1.3936. Min Act: -0.1700
Data Index: 3264575 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4640. Min Range: -1.4640
Max Act: 1.3936. Min Act: -0.1700
Data Index: 6313636 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4640. Min Range: -1.4640
Max Act: 1.4200. Min Act: -0.1700
Data Index: 7147594 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4640. Min Range: -1.4640
Max Act: 1.4024. Min Act: -0.1700
Data Index: 2897579 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4640. Min Range: -1.4640
Max Act: 1.3936. Min Act: -0.1700
Data Index: 2680356 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4640. Min Range: -1.4640
Max Act: 1.4024. Min Act: -0.1700
Data Index: 1379051 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4640. Min Range: -1.4640
Max Act: 1.3936. Min Act: -0.1700
Data Index: 3439968 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4640. Min Range: -1.4640
Max Act: 1.3936. Min Act: -0.1700
Data Index: 8361382 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4640. Min Range: -1.4640
Max Act: 1.3936. Min Act: -0.1700
Data Index: 5223818 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4640. Min Range: -1.4640
Max Act: 1.4024. Min Act: -0.1700
Data Index: 1842827 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4640. Min Range: -1.4640
Max Act: 1.3848. Min Act: -0.1700
Data Index: 2698228 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19