Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3624 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4208. Min Range: -3.4208
Max Act: 3.4208. Min Act: -0.1700
Data Index: 4363556 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4208. Min Range: -3.4208
Max Act: 3.3894. Min Act: -0.1700
Data Index: 4106995 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4208. Min Range: -3.4208
Max Act: 3.3581. Min Act: -0.1700
Data Index: 8556375 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4208. Min Range: -3.4208
Max Act: 3.3581. Min Act: -0.1700
Data Index: 7549325 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4208. Min Range: -3.4208
Max Act: 3.3581. Min Act: -0.1700
Data Index: 7302844 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4208. Min Range: -3.4208
Max Act: 3.3581. Min Act: -0.1700
Data Index: 7636436 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4208. Min Range: -3.4208
Max Act: 3.3424. Min Act: -0.1700
Data Index: 6091065 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4208. Min Range: -3.4208
Max Act: 3.3267. Min Act: -0.1700
Data Index: 6645988 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4208. Min Range: -3.4208
Max Act: 3.3267. Min Act: -0.1700
Data Index: 2817232 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4208. Min Range: -3.4208
Max Act: 3.3110. Min Act: -0.1700
Data Index: 1968915 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4208. Min Range: -3.4208
Max Act: 3.2953. Min Act: -0.1700
Data Index: 3875709 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4208. Min Range: -3.4208
Max Act: 3.2796. Min Act: -0.1700
Data Index: 1978614 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4208. Min Range: -3.4208
Max Act: 3.2639. Min Act: -0.1700
Data Index: 78802 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4208. Min Range: -3.4208
Max Act: 3.2639. Min Act: -0.1700
Data Index: 6599276 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4208. Min Range: -3.4208
Max Act: 3.2796. Min Act: -0.1700
Data Index: 8432103 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4208. Min Range: -3.4208
Max Act: 3.2482. Min Act: -0.1700
Data Index: 4508142 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4208. Min Range: -3.4208
Max Act: 3.2482. Min Act: -0.1700
Data Index: 10113 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4208. Min Range: -3.4208
Max Act: 3.2482. Min Act: -0.1700
Data Index: 6504825 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4208. Min Range: -3.4208
Max Act: 3.2324. Min Act: -0.1700
Data Index: 3588030 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4208. Min Range: -3.4208
Max Act: 3.2482. Min Act: -0.1700
Data Index: 680467 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19