Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4072 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8593. Min Range: -4.8593
Max Act: 4.8593. Min Act: -0.1700
Data Index: 8287023 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8593. Min Range: -4.8593
Max Act: 4.7968. Min Act: -0.1700
Data Index: 478098 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8593. Min Range: -4.8593
Max Act: 4.7343. Min Act: -0.1700
Data Index: 4357046 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8593. Min Range: -4.8593
Max Act: 4.6405. Min Act: -0.1700
Data Index: 6136175 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8593. Min Range: -4.8593
Max Act: 4.6093. Min Act: -0.1700
Data Index: 7807985 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8593. Min Range: -4.8593
Max Act: 4.6405. Min Act: -0.1700
Data Index: 7385427 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8593. Min Range: -4.8593
Max Act: 4.6093. Min Act: -0.1700
Data Index: 5890957 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8593. Min Range: -4.8593
Max Act: 4.6093. Min Act: -0.1700
Data Index: 2819742 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8593. Min Range: -4.8593
Max Act: 4.5780. Min Act: -0.1700
Data Index: 2702265 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8593. Min Range: -4.8593
Max Act: 4.5780. Min Act: -0.1700
Data Index: 624910 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8593. Min Range: -4.8593
Max Act: 4.6093. Min Act: -0.1700
Data Index: 1489108 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8593. Min Range: -4.8593
Max Act: 4.5468. Min Act: -0.1700
Data Index: 368574 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8593. Min Range: -4.8593
Max Act: 4.5155. Min Act: -0.1700
Data Index: 4835036 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8593. Min Range: -4.8593
Max Act: 4.5155. Min Act: -0.1700
Data Index: 1299470 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8593. Min Range: -4.8593
Max Act: 4.5468. Min Act: -0.1700
Data Index: 6924273 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8593. Min Range: -4.8593
Max Act: 4.5780. Min Act: -0.1700
Data Index: 3633411 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8593. Min Range: -4.8593
Max Act: 4.5155. Min Act: -0.1700
Data Index: 7003191 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8593. Min Range: -4.8593
Max Act: 4.5155. Min Act: -0.1700
Data Index: 4181450 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8593. Min Range: -4.8593
Max Act: 4.5155. Min Act: -0.1700
Data Index: 4229833 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8593. Min Range: -4.8593
Max Act: 4.5155. Min Act: -0.1700
Data Index: 6442056 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19