Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 598 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6677. Min Range: -2.6677
Max Act: 2.6677. Min Act: -0.1700
Data Index: 6186888 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6677. Min Range: -2.6677
Max Act: 2.6196. Min Act: -0.1700
Data Index: 6258266 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6677. Min Range: -2.6677
Max Act: 2.6035. Min Act: -0.1700
Data Index: 8100884 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6677. Min Range: -2.6677
Max Act: 2.6035. Min Act: -0.1700
Data Index: 8682243 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6677. Min Range: -2.6677
Max Act: 2.5874. Min Act: -0.1700
Data Index: 7863148 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6677. Min Range: -2.6677
Max Act: 2.5713. Min Act: -0.1700
Data Index: 1068852 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6677. Min Range: -2.6677
Max Act: 2.5551. Min Act: -0.1700
Data Index: 3961786 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6677. Min Range: -2.6677
Max Act: 2.4904. Min Act: -0.1700
Data Index: 1936273 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6677. Min Range: -2.6677
Max Act: 2.4904. Min Act: -0.1700
Data Index: 4785233 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6677. Min Range: -2.6677
Max Act: 2.4904. Min Act: -0.1700
Data Index: 2147686 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6677. Min Range: -2.6677
Max Act: 2.4742. Min Act: -0.1700
Data Index: 4897825 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6677. Min Range: -2.6677
Max Act: 2.4742. Min Act: -0.1700
Data Index: 2376172 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6677. Min Range: -2.6677
Max Act: 2.4742. Min Act: -0.1700
Data Index: 4427012 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6677. Min Range: -2.6677
Max Act: 2.4742. Min Act: -0.1700
Data Index: 4337653 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6677. Min Range: -2.6677
Max Act: 2.4580. Min Act: -0.1700
Data Index: 4205238 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6677. Min Range: -2.6677
Max Act: 2.4742. Min Act: -0.1700
Data Index: 5277818 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6677. Min Range: -2.6677
Max Act: 2.4580. Min Act: -0.1700
Data Index: 3418981 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6677. Min Range: -2.6677
Max Act: 2.4580. Min Act: -0.1700
Data Index: 6030172 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6677. Min Range: -2.6677
Max Act: 2.4580. Min Act: -0.1700
Data Index: 75577 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6677. Min Range: -2.6677
Max Act: 2.4580. Min Act: -0.1700
Data Index: 4636162 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19