Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 991 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7964. Min Range: -3.7964
Max Act: 3.7964. Min Act: -0.1700
Data Index: 1233427 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7964. Min Range: -3.7964
Max Act: 3.7652. Min Act: -0.1700
Data Index: 5144908 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7964. Min Range: -3.7964
Max Act: 3.7652. Min Act: -0.1700
Data Index: 4443080 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7964. Min Range: -3.7964
Max Act: 3.7339. Min Act: -0.1700
Data Index: 4172669 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7964. Min Range: -3.7964
Max Act: 3.7026. Min Act: -0.1700
Data Index: 942745 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7964. Min Range: -3.7964
Max Act: 3.7026. Min Act: -0.1700
Data Index: 7476980 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7964. Min Range: -3.7964
Max Act: 3.6870. Min Act: -0.1700
Data Index: 5165446 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7964. Min Range: -3.7964
Max Act: 3.7026. Min Act: -0.1700
Data Index: 1463602 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7964. Min Range: -3.7964
Max Act: 3.6713. Min Act: -0.1700
Data Index: 3420575 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7964. Min Range: -3.7964
Max Act: 3.6557. Min Act: -0.1700
Data Index: 2997180 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7964. Min Range: -3.7964
Max Act: 3.6557. Min Act: -0.1700
Data Index: 1194477 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7964. Min Range: -3.7964
Max Act: 3.6557. Min Act: -0.1700
Data Index: 6085147 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7964. Min Range: -3.7964
Max Act: 3.6557. Min Act: -0.1700
Data Index: 4924296 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7964. Min Range: -3.7964
Max Act: 3.6400. Min Act: -0.1700
Data Index: 1399693 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7964. Min Range: -3.7964
Max Act: 3.6870. Min Act: -0.1700
Data Index: 2817417 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7964. Min Range: -3.7964
Max Act: 3.6400. Min Act: -0.1700
Data Index: 38943 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7964. Min Range: -3.7964
Max Act: 3.6400. Min Act: -0.1700
Data Index: 4398345 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7964. Min Range: -3.7964
Max Act: 3.6400. Min Act: -0.1700
Data Index: 269063 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7964. Min Range: -3.7964
Max Act: 3.6244. Min Act: -0.1700
Data Index: 2479263 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7964. Min Range: -3.7964
Max Act: 3.6400. Min Act: -0.1700
Data Index: 1185808 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19