Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3384 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9487. Min Range: -3.9487
Max Act: 3.9487. Min Act: -0.1700
Data Index: 5012087 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9487. Min Range: -3.9487
Max Act: 3.9174. Min Act: -0.1700
Data Index: 2095092 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9487. Min Range: -3.9487
Max Act: 3.8861. Min Act: -0.1700
Data Index: 224606 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9487. Min Range: -3.9487
Max Act: 3.8861. Min Act: -0.1700
Data Index: 996545 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9487. Min Range: -3.9487
Max Act: 3.8549. Min Act: -0.1700
Data Index: 4054484 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9487. Min Range: -3.9487
Max Act: 3.8549. Min Act: -0.1700
Data Index: 5733515 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9487. Min Range: -3.9487
Max Act: 3.8236. Min Act: -0.1700
Data Index: 379498 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9487. Min Range: -3.9487
Max Act: 3.8236. Min Act: -0.1700
Data Index: 8528677 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9487. Min Range: -3.9487
Max Act: 3.8236. Min Act: -0.1700
Data Index: 912597 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9487. Min Range: -3.9487
Max Act: 3.7923. Min Act: -0.1700
Data Index: 3041682 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9487. Min Range: -3.9487
Max Act: 3.7923. Min Act: -0.1700
Data Index: 2304591 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9487. Min Range: -3.9487
Max Act: 3.7923. Min Act: -0.1700
Data Index: 5192725 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9487. Min Range: -3.9487
Max Act: 3.7610. Min Act: -0.1700
Data Index: 667110 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9487. Min Range: -3.9487
Max Act: 3.7610. Min Act: -0.1700
Data Index: 6761050 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9487. Min Range: -3.9487
Max Act: 3.7610. Min Act: -0.1700
Data Index: 6064548 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9487. Min Range: -3.9487
Max Act: 3.7610. Min Act: -0.1700
Data Index: 4716345 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9487. Min Range: -3.9487
Max Act: 3.7298. Min Act: -0.1700
Data Index: 6164955 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9487. Min Range: -3.9487
Max Act: 3.6985. Min Act: -0.1700
Data Index: 1160518 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9487. Min Range: -3.9487
Max Act: 3.6985. Min Act: -0.1700
Data Index: 4282986 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9487. Min Range: -3.9487
Max Act: 3.6985. Min Act: -0.1700
Data Index: 4981212 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19