Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2897 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8076. Min Range: -7.8076
Max Act: 7.8076. Min Act: -0.1700
Data Index: 1259994 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8076. Min Range: -7.8076
Max Act: 7.4951. Min Act: -0.1700
Data Index: 1203006 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8076. Min Range: -7.8076
Max Act: 7.5263. Min Act: -0.1700
Data Index: 8784958 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8076. Min Range: -7.8076
Max Act: 7.4638. Min Act: -0.1700
Data Index: 4830421 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8076. Min Range: -7.8076
Max Act: 7.3701. Min Act: -0.1700
Data Index: 7597805 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8076. Min Range: -7.8076
Max Act: 7.3388. Min Act: -0.1700
Data Index: 5587760 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8076. Min Range: -7.8076
Max Act: 7.3076. Min Act: -0.1700
Data Index: 5089133 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8076. Min Range: -7.8076
Max Act: 7.3388. Min Act: -0.1700
Data Index: 6819815 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8076. Min Range: -7.8076
Max Act: 7.3076. Min Act: -0.1700
Data Index: 869461 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8076. Min Range: -7.8076
Max Act: 7.3076. Min Act: -0.1700
Data Index: 1912431 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8076. Min Range: -7.8076
Max Act: 7.3076. Min Act: -0.1700
Data Index: 4178811 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8076. Min Range: -7.8076
Max Act: 7.2763. Min Act: -0.1700
Data Index: 6009070 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8076. Min Range: -7.8076
Max Act: 7.2451. Min Act: -0.1700
Data Index: 4293916 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8076. Min Range: -7.8076
Max Act: 7.2763. Min Act: -0.1700
Data Index: 7391707 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8076. Min Range: -7.8076
Max Act: 7.2451. Min Act: -0.1700
Data Index: 4733390 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8076. Min Range: -7.8076
Max Act: 7.2763. Min Act: -0.1700
Data Index: 1507230 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8076. Min Range: -7.8076
Max Act: 7.2138. Min Act: -0.1700
Data Index: 3471259 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8076. Min Range: -7.8076
Max Act: 7.2138. Min Act: -0.1700
Data Index: 4863829 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8076. Min Range: -7.8076
Max Act: 7.2138. Min Act: -0.1700
Data Index: 7105409 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8076. Min Range: -7.8076
Max Act: 7.1826. Min Act: -0.1700
Data Index: 1650859 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19