Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2803 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6990. Min Range: -5.6990
Max Act: 5.6990. Min Act: -0.1700
Data Index: 8278856 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6990. Min Range: -5.6990
Max Act: 5.6677. Min Act: -0.1700
Data Index: 3231022 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6990. Min Range: -5.6990
Max Act: 5.6677. Min Act: -0.1700
Data Index: 7775538 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6990. Min Range: -5.6990
Max Act: 5.6677. Min Act: -0.1700
Data Index: 6268298 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6990. Min Range: -5.6990
Max Act: 5.6365. Min Act: -0.1700
Data Index: 3254143 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6990. Min Range: -5.6990
Max Act: 5.6365. Min Act: -0.1700
Data Index: 8827378 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6990. Min Range: -5.6990
Max Act: 5.6365. Min Act: -0.1700
Data Index: 2074785 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6990. Min Range: -5.6990
Max Act: 5.6052. Min Act: -0.1700
Data Index: 4944652 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6990. Min Range: -5.6990
Max Act: 5.6365. Min Act: -0.1700
Data Index: 2020534 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6990. Min Range: -5.6990
Max Act: 5.6365. Min Act: -0.1700
Data Index: 4830420 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6990. Min Range: -5.6990
Max Act: 5.6365. Min Act: -0.1700
Data Index: 1652073 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6990. Min Range: -5.6990
Max Act: 5.6365. Min Act: -0.1700
Data Index: 3732114 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6990. Min Range: -5.6990
Max Act: 5.6052. Min Act: -0.1700
Data Index: 1286920 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6990. Min Range: -5.6990
Max Act: 5.6052. Min Act: -0.1700
Data Index: 2526618 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6990. Min Range: -5.6990
Max Act: 5.6052. Min Act: -0.1700
Data Index: 1324664 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6990. Min Range: -5.6990
Max Act: 5.6052. Min Act: -0.1700
Data Index: 254145 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6990. Min Range: -5.6990
Max Act: 5.6052. Min Act: -0.1700
Data Index: 2858017 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6990. Min Range: -5.6990
Max Act: 5.6052. Min Act: -0.1700
Data Index: 797564 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6990. Min Range: -5.6990
Max Act: 5.6052. Min Act: -0.1700
Data Index: 295036 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6990. Min Range: -5.6990
Max Act: 5.6052. Min Act: -0.1700
Data Index: 2900029 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19