Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2452 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5466. Min Range: -2.5466
Max Act: 2.5466. Min Act: -0.1700
Data Index: 1161017 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5466. Min Range: -2.5466
Max Act: 2.5142. Min Act: -0.1700
Data Index: 816733 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5466. Min Range: -2.5466
Max Act: 2.4818. Min Act: -0.1700
Data Index: 1581425 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5466. Min Range: -2.5466
Max Act: 2.4494. Min Act: -0.1700
Data Index: 2298426 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5466. Min Range: -2.5466
Max Act: 2.4331. Min Act: -0.1700
Data Index: 3718876 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5466. Min Range: -2.5466
Max Act: 2.4331. Min Act: -0.1700
Data Index: 7778300 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5466. Min Range: -2.5466
Max Act: 2.4331. Min Act: -0.1700
Data Index: 5375198 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5466. Min Range: -2.5466
Max Act: 2.4331. Min Act: -0.1700
Data Index: 3945532 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5466. Min Range: -2.5466
Max Act: 2.4168. Min Act: -0.1700
Data Index: 7259043 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5466. Min Range: -2.5466
Max Act: 2.4005. Min Act: -0.1700
Data Index: 6162774 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5466. Min Range: -2.5466
Max Act: 2.3678. Min Act: -0.1700
Data Index: 7833852 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5466. Min Range: -2.5466
Max Act: 2.3842. Min Act: -0.1700
Data Index: 1841628 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5466. Min Range: -2.5466
Max Act: 2.3678. Min Act: -0.1700
Data Index: 5153545 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5466. Min Range: -2.5466
Max Act: 2.3842. Min Act: -0.1700
Data Index: 8254213 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5466. Min Range: -2.5466
Max Act: 2.3842. Min Act: -0.1700
Data Index: 6846420 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5466. Min Range: -2.5466
Max Act: 2.3842. Min Act: -0.1700
Data Index: 1735103 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5466. Min Range: -2.5466
Max Act: 2.3842. Min Act: -0.1700
Data Index: 2986388 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5466. Min Range: -2.5466
Max Act: 2.3678. Min Act: -0.1700
Data Index: 5945171 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5466. Min Range: -2.5466
Max Act: 2.3678. Min Act: -0.1700
Data Index: 3542354 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5466. Min Range: -2.5466
Max Act: 2.3350. Min Act: -0.1700
Data Index: 6478108 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19