Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4023 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5994. Min Range: -1.5994
Max Act: 1.5819. Min Act: -0.1700
Data Index: 3411414 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5994. Min Range: -1.5994
Max Act: 1.5994. Min Act: -0.1700
Data Index: 3108221 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5994. Min Range: -1.5994
Max Act: 1.5294. Min Act: -0.1700
Data Index: 2061696 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5994. Min Range: -1.5994
Max Act: 1.5381. Min Act: -0.1700
Data Index: 5779730 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5994. Min Range: -1.5994
Max Act: 1.5206. Min Act: -0.1700
Data Index: 3250609 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5994. Min Range: -1.5994
Max Act: 1.5294. Min Act: -0.1700
Data Index: 5105992 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5994. Min Range: -1.5994
Max Act: 1.5294. Min Act: -0.1700
Data Index: 6677787 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5994. Min Range: -1.5994
Max Act: 1.5206. Min Act: -0.1700
Data Index: 6836216 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5994. Min Range: -1.5994
Max Act: 1.5118. Min Act: -0.1700
Data Index: 6749196 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5994. Min Range: -1.5994
Max Act: 1.5118. Min Act: -0.1700
Data Index: 4427046 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5994. Min Range: -1.5994
Max Act: 1.5030. Min Act: -0.1700
Data Index: 8266136 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5994. Min Range: -1.5994
Max Act: 1.5030. Min Act: -0.1700
Data Index: 5474918 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5994. Min Range: -1.5994
Max Act: 1.4943. Min Act: -0.1700
Data Index: 1917552 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5994. Min Range: -1.5994
Max Act: 1.5030. Min Act: -0.1697
Data Index: 7789611 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5994. Min Range: -1.5994
Max Act: 1.4943. Min Act: -0.1700
Data Index: 3126479 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5994. Min Range: -1.5994
Max Act: 1.5030. Min Act: -0.1700
Data Index: 5859778 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5994. Min Range: -1.5994
Max Act: 1.4943. Min Act: -0.1700
Data Index: 5598968 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5994. Min Range: -1.5994
Max Act: 1.4943. Min Act: -0.1700
Data Index: 4428274 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5994. Min Range: -1.5994
Max Act: 1.4855. Min Act: -0.1700
Data Index: 1190956 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5994. Min Range: -1.5994
Max Act: 1.4855. Min Act: -0.1697
Data Index: 4288053 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19