Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2617 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.6081. Min Act: -0.1700
Data Index: 253135 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.5456. Min Act: -0.1700
Data Index: 3741645 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.5456. Min Act: -0.1700
Data Index: 6704590 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.5456. Min Act: -0.1700
Data Index: 6704586 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.5456. Min Act: -0.1700
Data Index: 3018859 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.5456. Min Act: -0.1700
Data Index: 6704606 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.5456. Min Act: -0.1700
Data Index: 6704613 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.5456. Min Act: -0.1700
Data Index: 2374088 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.5143. Min Act: -0.1700
Data Index: 3707354 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.5143. Min Act: -0.1700
Data Index: 3557570 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.5143. Min Act: -0.1700
Data Index: 5857802 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.5143. Min Act: -0.1700
Data Index: 7033159 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.4831. Min Act: -0.1700
Data Index: 3155452 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.5143. Min Act: -0.1700
Data Index: 4150386 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.5143. Min Act: -0.1700
Data Index: 2476731 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.5143. Min Act: -0.1699
Data Index: 6690252 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.4831. Min Act: -0.1700
Data Index: 4742680 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.5143. Min Act: -0.1700
Data Index: 4643912 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.5143. Min Act: -0.1700
Data Index: 4528102 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.4831. Min Act: -0.1700
Data Index: 6237062 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19