Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2909 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1945. Min Range: -5.1945
Max Act: 5.1945. Min Act: -0.1700
Data Index: 3993773 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1945. Min Range: -5.1945
Max Act: 5.1320. Min Act: -0.1700
Data Index: 4963450 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1945. Min Range: -5.1945
Max Act: 5.0695. Min Act: -0.1700
Data Index: 7125906 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1945. Min Range: -5.1945
Max Act: 5.0695. Min Act: -0.1700
Data Index: 8066166 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1945. Min Range: -5.1945
Max Act: 5.0695. Min Act: -0.1700
Data Index: 4657455 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1945. Min Range: -5.1945
Max Act: 5.0070. Min Act: -0.1700
Data Index: 2454683 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1945. Min Range: -5.1945
Max Act: 4.9757. Min Act: -0.1700
Data Index: 5661500 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1945. Min Range: -5.1945
Max Act: 5.0070. Min Act: -0.1700
Data Index: 2206567 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1945. Min Range: -5.1945
Max Act: 5.0070. Min Act: -0.1700
Data Index: 8207472 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1945. Min Range: -5.1945
Max Act: 5.0070. Min Act: -0.1700
Data Index: 7390985 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1945. Min Range: -5.1945
Max Act: 5.0382. Min Act: -0.1700
Data Index: 7201972 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1945. Min Range: -5.1945
Max Act: 5.0070. Min Act: -0.1700
Data Index: 4041229 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1945. Min Range: -5.1945
Max Act: 5.0070. Min Act: -0.1700
Data Index: 675958 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1945. Min Range: -5.1945
Max Act: 5.0070. Min Act: -0.1700
Data Index: 6440080 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1945. Min Range: -5.1945
Max Act: 5.0070. Min Act: -0.1700
Data Index: 3124870 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1945. Min Range: -5.1945
Max Act: 5.0070. Min Act: -0.1700
Data Index: 2549182 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1945. Min Range: -5.1945
Max Act: 4.9757. Min Act: -0.1700
Data Index: 5360038 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1945. Min Range: -5.1945
Max Act: 4.9757. Min Act: -0.1700
Data Index: 5553382 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1945. Min Range: -5.1945
Max Act: 4.9757. Min Act: -0.1700
Data Index: 1366012 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1945. Min Range: -5.1945
Max Act: 4.9757. Min Act: -0.1700
Data Index: 1570994 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19