Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2823 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9489. Min Range: -7.9489
Max Act: 7.9489. Min Act: -0.1700
Data Index: 6493248 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9489. Min Range: -7.9489
Max Act: 7.8864. Min Act: -0.1700
Data Index: 1032228 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9489. Min Range: -7.9489
Max Act: 7.8864. Min Act: -0.1700
Data Index: 6848868 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9489. Min Range: -7.9489
Max Act: 7.8239. Min Act: -0.1700
Data Index: 4895077 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9489. Min Range: -7.9489
Max Act: 7.7614. Min Act: -0.1700
Data Index: 1731196 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9489. Min Range: -7.9489
Max Act: 7.7614. Min Act: -0.1700
Data Index: 1831020 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9489. Min Range: -7.9489
Max Act: 7.5739. Min Act: -0.1700
Data Index: 8550464 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9489. Min Range: -7.9489
Max Act: 7.5426. Min Act: -0.1700
Data Index: 669991 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9489. Min Range: -7.9489
Max Act: 7.5426. Min Act: -0.1700
Data Index: 1947439 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9489. Min Range: -7.9489
Max Act: 7.5426. Min Act: -0.1700
Data Index: 4976851 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9489. Min Range: -7.9489
Max Act: 7.4489. Min Act: -0.1700
Data Index: 3949521 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9489. Min Range: -7.9489
Max Act: 7.4489. Min Act: -0.1700
Data Index: 2321645 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9489. Min Range: -7.9489
Max Act: 7.4176. Min Act: -0.1700
Data Index: 369174 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9489. Min Range: -7.9489
Max Act: 7.4176. Min Act: -0.1700
Data Index: 7993496 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9489. Min Range: -7.9489
Max Act: 7.3864. Min Act: -0.1700
Data Index: 7332239 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9489. Min Range: -7.9489
Max Act: 7.3551. Min Act: -0.1700
Data Index: 1481168 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9489. Min Range: -7.9489
Max Act: 7.3864. Min Act: -0.1700
Data Index: 7433701 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9489. Min Range: -7.9489
Max Act: 7.3864. Min Act: -0.1700
Data Index: 8182685 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9489. Min Range: -7.9489
Max Act: 7.3551. Min Act: -0.1700
Data Index: 1220314 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9489. Min Range: -7.9489
Max Act: 7.3864. Min Act: -0.1700
Data Index: 6731455 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19