Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1288 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3192. Min Range: -5.3192
Max Act: 5.3192. Min Act: -0.1700
Data Index: 4289654 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3192. Min Range: -5.3192
Max Act: 5.2255. Min Act: -0.1700
Data Index: 734625 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3192. Min Range: -5.3192
Max Act: 5.2255. Min Act: -0.1700
Data Index: 1502176 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3192. Min Range: -5.3192
Max Act: 5.1942. Min Act: -0.1700
Data Index: 7886549 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3192. Min Range: -5.3192
Max Act: 5.1942. Min Act: -0.1700
Data Index: 986718 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3192. Min Range: -5.3192
Max Act: 5.1630. Min Act: -0.1700
Data Index: 3557345 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3192. Min Range: -5.3192
Max Act: 5.1942. Min Act: -0.1700
Data Index: 6114309 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3192. Min Range: -5.3192
Max Act: 5.1942. Min Act: -0.1700
Data Index: 2861835 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3192. Min Range: -5.3192
Max Act: 5.1317. Min Act: -0.1700
Data Index: 914626 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3192. Min Range: -5.3192
Max Act: 5.1317. Min Act: -0.1700
Data Index: 6303227 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3192. Min Range: -5.3192
Max Act: 5.1317. Min Act: -0.1700
Data Index: 4641720 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3192. Min Range: -5.3192
Max Act: 5.1317. Min Act: -0.1700
Data Index: 3099264 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3192. Min Range: -5.3192
Max Act: 5.1317. Min Act: -0.1700
Data Index: 5763480 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3192. Min Range: -5.3192
Max Act: 5.1005. Min Act: -0.1700
Data Index: 8361785 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3192. Min Range: -5.3192
Max Act: 5.1005. Min Act: -0.1700
Data Index: 8476656 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3192. Min Range: -5.3192
Max Act: 5.1005. Min Act: -0.1700
Data Index: 8575714 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3192. Min Range: -5.3192
Max Act: 5.1005. Min Act: -0.1700
Data Index: 974095 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3192. Min Range: -5.3192
Max Act: 5.0692. Min Act: -0.1700
Data Index: 4535762 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3192. Min Range: -5.3192
Max Act: 5.0692. Min Act: -0.1700
Data Index: 1976006 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3192. Min Range: -5.3192
Max Act: 5.0692. Min Act: -0.1700
Data Index: 2133099 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19