Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5324 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7677. Min Range: -5.7677
Max Act: 5.7677. Min Act: -0.1700
Data Index: 2698031 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7677. Min Range: -5.7677
Max Act: 5.7052. Min Act: -0.1700
Data Index: 2686864 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7677. Min Range: -5.7677
Max Act: 5.6739. Min Act: -0.1700
Data Index: 467205 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7677. Min Range: -5.7677
Max Act: 5.6427. Min Act: -0.1700
Data Index: 2740853 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7677. Min Range: -5.7677
Max Act: 5.6427. Min Act: -0.1700
Data Index: 1664407 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7677. Min Range: -5.7677
Max Act: 5.6427. Min Act: -0.1700
Data Index: 1727900 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7677. Min Range: -5.7677
Max Act: 5.6427. Min Act: -0.1700
Data Index: 1664412 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7677. Min Range: -5.7677
Max Act: 5.5802. Min Act: -0.1700
Data Index: 8757082 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7677. Min Range: -5.7677
Max Act: 5.6114. Min Act: -0.1700
Data Index: 7633222 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7677. Min Range: -5.7677
Max Act: 5.5802. Min Act: -0.1700
Data Index: 6638811 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7677. Min Range: -5.7677
Max Act: 5.5802. Min Act: -0.1700
Data Index: 1664411 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7677. Min Range: -5.7677
Max Act: 5.6114. Min Act: -0.1700
Data Index: 8720142 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7677. Min Range: -5.7677
Max Act: 5.5489. Min Act: -0.1700
Data Index: 8720138 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7677. Min Range: -5.7677
Max Act: 5.5489. Min Act: -0.1700
Data Index: 8175325 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7677. Min Range: -5.7677
Max Act: 5.5489. Min Act: -0.1700
Data Index: 7633223 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7677. Min Range: -5.7677
Max Act: 5.5489. Min Act: -0.1700
Data Index: 3115433 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7677. Min Range: -5.7677
Max Act: 5.5489. Min Act: -0.1700
Data Index: 1700287 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7677. Min Range: -5.7677
Max Act: 5.5177. Min Act: -0.1700
Data Index: 5526394 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7677. Min Range: -5.7677
Max Act: 5.5177. Min Act: -0.1700
Data Index: 4643335 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7677. Min Range: -5.7677
Max Act: 5.4864. Min Act: -0.1700
Data Index: 2609959 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19