Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7333. Min Range: -3.7333
Max Act: 3.7333. Min Act: -0.1700
Data Index: 2727251 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7333. Min Range: -3.7333
Max Act: 3.7020. Min Act: -0.1700
Data Index: 8459400 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7333. Min Range: -3.7333
Max Act: 3.6708. Min Act: -0.1700
Data Index: 821189 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7333. Min Range: -3.7333
Max Act: 3.6708. Min Act: -0.1700
Data Index: 4706855 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7333. Min Range: -3.7333
Max Act: 3.6708. Min Act: -0.1700
Data Index: 6169996 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7333. Min Range: -3.7333
Max Act: 3.6395. Min Act: -0.1700
Data Index: 7250259 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7333. Min Range: -3.7333
Max Act: 3.6395. Min Act: -0.1700
Data Index: 3689719 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7333. Min Range: -3.7333
Max Act: 3.6082. Min Act: -0.1700
Data Index: 184121 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7333. Min Range: -3.7333
Max Act: 3.6082. Min Act: -0.1700
Data Index: 442789 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7333. Min Range: -3.7333
Max Act: 3.6082. Min Act: -0.1700
Data Index: 5204551 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7333. Min Range: -3.7333
Max Act: 3.6082. Min Act: -0.1700
Data Index: 5877443 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7333. Min Range: -3.7333
Max Act: 3.6082. Min Act: -0.1700
Data Index: 3006160 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7333. Min Range: -3.7333
Max Act: 3.6082. Min Act: -0.1700
Data Index: 304059 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7333. Min Range: -3.7333
Max Act: 3.6082. Min Act: -0.1700
Data Index: 3737374 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7333. Min Range: -3.7333
Max Act: 3.6082. Min Act: -0.1700
Data Index: 8117872 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7333. Min Range: -3.7333
Max Act: 3.5456. Min Act: -0.1700
Data Index: 6758370 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7333. Min Range: -3.7333
Max Act: 3.5769. Min Act: -0.1700
Data Index: 6545954 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7333. Min Range: -3.7333
Max Act: 3.5769. Min Act: -0.1700
Data Index: 4414948 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7333. Min Range: -3.7333
Max Act: 3.5456. Min Act: -0.1700
Data Index: 797031 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7333. Min Range: -3.7333
Max Act: 3.5456. Min Act: -0.1700
Data Index: 173434 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19