Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1888 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9133. Min Range: -2.9133
Max Act: 2.9133. Min Act: -0.1700
Data Index: 6195303 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9133. Min Range: -2.9133
Max Act: 2.8816. Min Act: -0.1700
Data Index: 3121319 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9133. Min Range: -2.9133
Max Act: 2.8657. Min Act: -0.1700
Data Index: 657391 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9133. Min Range: -2.9133
Max Act: 2.8657. Min Act: -0.1700
Data Index: 3136954 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9133. Min Range: -2.9133
Max Act: 2.8499. Min Act: -0.1700
Data Index: 7321639 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9133. Min Range: -2.9133
Max Act: 2.8499. Min Act: -0.1700
Data Index: 1515670 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9133. Min Range: -2.9133
Max Act: 2.8499. Min Act: -0.1700
Data Index: 2987367 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9133. Min Range: -2.9133
Max Act: 2.8340. Min Act: -0.1700
Data Index: 8292419 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9133. Min Range: -2.9133
Max Act: 2.8340. Min Act: -0.1700
Data Index: 1362442 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9133. Min Range: -2.9133
Max Act: 2.8340. Min Act: -0.1700
Data Index: 1077761 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9133. Min Range: -2.9133
Max Act: 2.8340. Min Act: -0.1700
Data Index: 2461388 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9133. Min Range: -2.9133
Max Act: 2.8181. Min Act: -0.1700
Data Index: 212014 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9133. Min Range: -2.9133
Max Act: 2.8181. Min Act: -0.1700
Data Index: 4435084 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9133. Min Range: -2.9133
Max Act: 2.8340. Min Act: -0.1700
Data Index: 4196940 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9133. Min Range: -2.9133
Max Act: 2.8181. Min Act: -0.1700
Data Index: 3265403 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9133. Min Range: -2.9133
Max Act: 2.8181. Min Act: -0.1700
Data Index: 6669325 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9133. Min Range: -2.9133
Max Act: 2.8021. Min Act: -0.1700
Data Index: 490748 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9133. Min Range: -2.9133
Max Act: 2.8181. Min Act: -0.1700
Data Index: 6584760 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9133. Min Range: -2.9133
Max Act: 2.8021. Min Act: -0.1700
Data Index: 1356211 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9133. Min Range: -2.9133
Max Act: 2.8021. Min Act: -0.1700
Data Index: 4703328 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19