Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8609. Min Range: -1.8609
Max Act: 1.8609. Min Act: -0.1700
Data Index: 7110083 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8609. Min Range: -1.8609
Max Act: 1.8609. Min Act: -0.1700
Data Index: 1185309 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8609. Min Range: -1.8609
Max Act: 1.8609. Min Act: -0.1700
Data Index: 4434656 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8609. Min Range: -1.8609
Max Act: 1.8437. Min Act: -0.1700
Data Index: 6029464 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8609. Min Range: -1.8609
Max Act: 1.8437. Min Act: -0.1700
Data Index: 2996268 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8609. Min Range: -1.8609
Max Act: 1.8266. Min Act: -0.1700
Data Index: 2807497 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8609. Min Range: -1.8609
Max Act: 1.8094. Min Act: -0.1700
Data Index: 251878 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8609. Min Range: -1.8609
Max Act: 1.8094. Min Act: -0.1700
Data Index: 5821960 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8609. Min Range: -1.8609
Max Act: 1.8094. Min Act: -0.1700
Data Index: 2363791 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8609. Min Range: -1.8609
Max Act: 1.8094. Min Act: -0.1698
Data Index: 7115022 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8609. Min Range: -1.8609
Max Act: 1.8094. Min Act: -0.1700
Data Index: 5546910 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8609. Min Range: -1.8609
Max Act: 1.8094. Min Act: -0.1700
Data Index: 2920403 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8609. Min Range: -1.8609
Max Act: 1.8094. Min Act: -0.1699
Data Index: 440461 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8609. Min Range: -1.8609
Max Act: 1.8094. Min Act: -0.1700
Data Index: 495961 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8609. Min Range: -1.8609
Max Act: 1.8094. Min Act: -0.1700
Data Index: 2858646 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8609. Min Range: -1.8609
Max Act: 1.8094. Min Act: -0.1700
Data Index: 4457606 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8609. Min Range: -1.8609
Max Act: 1.7922. Min Act: -0.1700
Data Index: 1604370 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8609. Min Range: -1.8609
Max Act: 1.7922. Min Act: -0.1700
Data Index: 1229385 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8609. Min Range: -1.8609
Max Act: 1.7922. Min Act: -0.1700
Data Index: 148962 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8609. Min Range: -1.8609
Max Act: 1.7750. Min Act: -0.1700
Data Index: 5547543 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19