Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2048 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7816. Min Range: -1.7816
Max Act: 1.7816. Min Act: -0.1700
Data Index: 2014418 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7816. Min Range: -1.7816
Max Act: 1.7557. Min Act: -0.1700
Data Index: 2483078 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7816. Min Range: -1.7816
Max Act: 1.7557. Min Act: -0.1700
Data Index: 6822312 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7816. Min Range: -1.7816
Max Act: 1.7384. Min Act: -0.1700
Data Index: 4802322 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7816. Min Range: -1.7816
Max Act: 1.7384. Min Act: -0.1700
Data Index: 3435301 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7816. Min Range: -1.7816
Max Act: 1.7297. Min Act: -0.1700
Data Index: 1854421 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7816. Min Range: -1.7816
Max Act: 1.7384. Min Act: -0.1699
Data Index: 8097879 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7816. Min Range: -1.7816
Max Act: 1.7124. Min Act: -0.1700
Data Index: 2621425 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7816. Min Range: -1.7816
Max Act: 1.7124. Min Act: -0.1700
Data Index: 5061130 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7816. Min Range: -1.7816
Max Act: 1.7124. Min Act: -0.1662
Data Index: 6692275 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7816. Min Range: -1.7816
Max Act: 1.7124. Min Act: -0.1700
Data Index: 3925125 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7816. Min Range: -1.7816
Max Act: 1.7038. Min Act: -0.1697
Data Index: 4806942 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7816. Min Range: -1.7816
Max Act: 1.7038. Min Act: -0.1700
Data Index: 958194 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7816. Min Range: -1.7816
Max Act: 1.6951. Min Act: -0.1700
Data Index: 1666850 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7816. Min Range: -1.7816
Max Act: 1.6864. Min Act: -0.1700
Data Index: 8097882 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7816. Min Range: -1.7816
Max Act: 1.6864. Min Act: -0.1700
Data Index: 6041778 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7816. Min Range: -1.7816
Max Act: 1.6864. Min Act: -0.1700
Data Index: 8165986 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7816. Min Range: -1.7816
Max Act: 1.6951. Min Act: -0.1700
Data Index: 5844483 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7816. Min Range: -1.7816
Max Act: 1.6864. Min Act: -0.1700
Data Index: 6041344 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7816. Min Range: -1.7816
Max Act: 1.6864. Min Act: -0.1700
Data Index: 6768330 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19