Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 895 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2783. Min Range: -7.2783
Max Act: 7.2783. Min Act: -0.1700
Data Index: 390665 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2783. Min Range: -7.2783
Max Act: 7.0908. Min Act: -0.1700
Data Index: 1770097 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2783. Min Range: -7.2783
Max Act: 6.9970. Min Act: -0.1700
Data Index: 390666 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2783. Min Range: -7.2783
Max Act: 6.9345. Min Act: -0.1700
Data Index: 4630492 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2783. Min Range: -7.2783
Max Act: 6.9033. Min Act: -0.1700
Data Index: 3818037 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2783. Min Range: -7.2783
Max Act: 6.9345. Min Act: -0.1700
Data Index: 6871221 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2783. Min Range: -7.2783
Max Act: 6.9033. Min Act: -0.1700
Data Index: 1770102 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2783. Min Range: -7.2783
Max Act: 6.7783. Min Act: -0.1700
Data Index: 7928950 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2783. Min Range: -7.2783
Max Act: 6.8720. Min Act: -0.1700
Data Index: 5518858 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2783. Min Range: -7.2783
Max Act: 6.8720. Min Act: -0.1700
Data Index: 8582245 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2783. Min Range: -7.2783
Max Act: 6.7783. Min Act: -0.1700
Data Index: 3678573 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2783. Min Range: -7.2783
Max Act: 6.7470. Min Act: -0.1700
Data Index: 2846403 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2783. Min Range: -7.2783
Max Act: 6.7470. Min Act: -0.1700
Data Index: 3408170 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2783. Min Range: -7.2783
Max Act: 6.6845. Min Act: -0.1700
Data Index: 3678572 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2783. Min Range: -7.2783
Max Act: 6.6845. Min Act: -0.1700
Data Index: 3408169 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2783. Min Range: -7.2783
Max Act: 6.5595. Min Act: -0.1700
Data Index: 3680686 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2783. Min Range: -7.2783
Max Act: 6.5595. Min Act: -0.1700
Data Index: 5662815 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2783. Min Range: -7.2783
Max Act: 6.4970. Min Act: -0.1700
Data Index: 2939758 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2783. Min Range: -7.2783
Max Act: 6.4658. Min Act: -0.1700
Data Index: 5483139 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2783. Min Range: -7.2783
Max Act: 6.5283. Min Act: -0.1700
Data Index: 3668578 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19