Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3289 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.4965. Min Act: -0.1700
Data Index: 3681422 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.3554. Min Act: -0.1700
Data Index: 4756077 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.3241. Min Act: -0.1700
Data Index: 2207179 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.3241. Min Act: -0.1700
Data Index: 6679042 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.3084. Min Act: -0.1700
Data Index: 6075322 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2927. Min Act: -0.1700
Data Index: 5601950 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2770. Min Act: -0.1700
Data Index: 1539224 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2770. Min Act: -0.1700
Data Index: 8574188 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2613. Min Act: -0.1700
Data Index: 4550375 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2455. Min Act: -0.1700
Data Index: 8161535 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2141. Min Act: -0.1700
Data Index: 1336139 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2298. Min Act: -0.1700
Data Index: 279187 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2298. Min Act: -0.1700
Data Index: 7138984 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2141. Min Act: -0.1700
Data Index: 4937075 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2141. Min Act: -0.1700
Data Index: 4887889 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2141. Min Act: -0.1700
Data Index: 8369366 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2141. Min Act: -0.1700
Data Index: 8462847 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2141. Min Act: -0.1700
Data Index: 6286330 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.1984. Min Act: -0.1700
Data Index: 7775790 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.1984. Min Act: -0.1700
Data Index: 6551254 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19