Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2950 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1869. Min Range: -7.1869
Max Act: 7.1869. Min Act: -0.1700
Data Index: 4581604 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1869. Min Range: -7.1869
Max Act: 7.0931. Min Act: -0.1700
Data Index: 4425760 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1869. Min Range: -7.1869
Max Act: 7.0619. Min Act: -0.1700
Data Index: 1215897 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1869. Min Range: -7.1869
Max Act: 6.9994. Min Act: -0.1700
Data Index: 2163065 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1869. Min Range: -7.1869
Max Act: 6.9994. Min Act: -0.1700
Data Index: 69988 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1869. Min Range: -7.1869
Max Act: 6.9994. Min Act: -0.1699
Data Index: 1600732 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1869. Min Range: -7.1869
Max Act: 6.9994. Min Act: -0.1700
Data Index: 605148 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1869. Min Range: -7.1869
Max Act: 6.9994. Min Act: -0.1700
Data Index: 1748302 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1869. Min Range: -7.1869
Max Act: 6.9369. Min Act: -0.1700
Data Index: 4123827 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1869. Min Range: -7.1869
Max Act: 6.9681. Min Act: -0.1700
Data Index: 2623528 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1869. Min Range: -7.1869
Max Act: 6.9681. Min Act: -0.1700
Data Index: 850972 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1869. Min Range: -7.1869
Max Act: 6.9681. Min Act: -0.1700
Data Index: 4619780 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1869. Min Range: -7.1869
Max Act: 6.9369. Min Act: -0.1700
Data Index: 7784706 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1869. Min Range: -7.1869
Max Act: 6.9681. Min Act: -0.1700
Data Index: 3794502 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1869. Min Range: -7.1869
Max Act: 6.9056. Min Act: -0.1700
Data Index: 7364647 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1869. Min Range: -7.1869
Max Act: 6.9369. Min Act: -0.1700
Data Index: 1289722 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1869. Min Range: -7.1869
Max Act: 6.9369. Min Act: -0.1700
Data Index: 5667537 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1869. Min Range: -7.1869
Max Act: 6.9056. Min Act: -0.1700
Data Index: 4553265 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1869. Min Range: -7.1869
Max Act: 6.9369. Min Act: -0.1700
Data Index: 1310558 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1869. Min Range: -7.1869
Max Act: 6.9369. Min Act: -0.1700
Data Index: 1917962 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19