Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1978 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.6658. Min Range: -1.6658
Max Act: 1.6658. Min Act: -0.1700
Data Index: 7680844 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6658. Min Range: -1.6658
Max Act: 1.6136. Min Act: -0.1700
Data Index: 4539539 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6658. Min Range: -1.6658
Max Act: 1.5961. Min Act: -0.1700
Data Index: 2485151 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6658. Min Range: -1.6658
Max Act: 1.5786. Min Act: -0.1700
Data Index: 6638739 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6658. Min Range: -1.6658
Max Act: 1.5611. Min Act: -0.1700
Data Index: 856545 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6658. Min Range: -1.6658
Max Act: 1.5786. Min Act: -0.1700
Data Index: 8750821 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6658. Min Range: -1.6658
Max Act: 1.5436. Min Act: -0.1700
Data Index: 8017786 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6658. Min Range: -1.6658
Max Act: 1.5261. Min Act: -0.1700
Data Index: 6087132 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6658. Min Range: -1.6658
Max Act: 1.5085. Min Act: -0.1700
Data Index: 3824254 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6658. Min Range: -1.6658
Max Act: 1.5085. Min Act: -0.1700
Data Index: 4365688 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6658. Min Range: -1.6658
Max Act: 1.4910. Min Act: -0.1700
Data Index: 6380320 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6658. Min Range: -1.6658
Max Act: 1.4910. Min Act: -0.1700
Data Index: 8464217 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6658. Min Range: -1.6658
Max Act: 1.4558. Min Act: -0.1700
Data Index: 6155210 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6658. Min Range: -1.6658
Max Act: 1.4558. Min Act: -0.1700
Data Index: 4007811 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6658. Min Range: -1.6658
Max Act: 1.4294. Min Act: -0.1700
Data Index: 7827127 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6658. Min Range: -1.6658
Max Act: 1.4294. Min Act: -0.1700
Data Index: 4442268 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6658. Min Range: -1.6658
Max Act: 1.4382. Min Act: -0.1700
Data Index: 3263016 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6658. Min Range: -1.6658
Max Act: 1.4118. Min Act: -0.1700
Data Index: 8718335 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6658. Min Range: -1.6658
Max Act: 1.4294. Min Act: -0.1700
Data Index: 3536404 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6658. Min Range: -1.6658
Max Act: 1.4030. Min Act: -0.1700
Data Index: 5889481 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19