Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 970 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0759. Min Range: -4.0759
Max Act: 4.0759. Min Act: -0.1700
Data Index: 7918620 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0759. Min Range: -4.0759
Max Act: 3.9353. Min Act: -0.1700
Data Index: 4605597 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0759. Min Range: -4.0759
Max Act: 3.8727. Min Act: -0.1700
Data Index: 625312 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0759. Min Range: -4.0759
Max Act: 3.8727. Min Act: -0.1700
Data Index: 279260 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0759. Min Range: -4.0759
Max Act: 3.8258. Min Act: -0.1700
Data Index: 4919633 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0759. Min Range: -4.0759
Max Act: 3.8258. Min Act: -0.1700
Data Index: 3266355 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0759. Min Range: -4.0759
Max Act: 3.7945. Min Act: -0.1700
Data Index: 4890361 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0759. Min Range: -4.0759
Max Act: 3.7945. Min Act: -0.1700
Data Index: 4449308 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0759. Min Range: -4.0759
Max Act: 3.7945. Min Act: -0.1700
Data Index: 6574386 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0759. Min Range: -4.0759
Max Act: 3.7945. Min Act: -0.1700
Data Index: 1175601 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0759. Min Range: -4.0759
Max Act: 3.7633. Min Act: -0.1700
Data Index: 5731767 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0759. Min Range: -4.0759
Max Act: 3.7476. Min Act: -0.1700
Data Index: 3594505 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0759. Min Range: -4.0759
Max Act: 3.7320. Min Act: -0.1700
Data Index: 256518 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0759. Min Range: -4.0759
Max Act: 3.7476. Min Act: -0.1700
Data Index: 3269770 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0759. Min Range: -4.0759
Max Act: 3.7163. Min Act: -0.1700
Data Index: 8203735 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0759. Min Range: -4.0759
Max Act: 3.7163. Min Act: -0.1700
Data Index: 7707676 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0759. Min Range: -4.0759
Max Act: 3.7163. Min Act: -0.1700
Data Index: 6988538 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0759. Min Range: -4.0759
Max Act: 3.7163. Min Act: -0.1700
Data Index: 714776 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0759. Min Range: -4.0759
Max Act: 3.7163. Min Act: -0.1700
Data Index: 1081142 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0759. Min Range: -4.0759
Max Act: 3.7163. Min Act: -0.1700
Data Index: 392595 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19