Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4996 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9793. Min Range: -6.9793
Max Act: 6.9793. Min Act: -0.1700
Data Index: 4485197 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9793. Min Range: -6.9793
Max Act: 6.8543. Min Act: -0.1700
Data Index: 8559652 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9793. Min Range: -6.9793
Max Act: 6.7918. Min Act: -0.1700
Data Index: 7871298 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9793. Min Range: -6.9793
Max Act: 6.7293. Min Act: -0.1700
Data Index: 7691883 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9793. Min Range: -6.9793
Max Act: 6.7605. Min Act: -0.1700
Data Index: 5807724 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9793. Min Range: -6.9793
Max Act: 6.7605. Min Act: -0.1700
Data Index: 2891434 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9793. Min Range: -6.9793
Max Act: 6.7605. Min Act: -0.1700
Data Index: 7053445 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9793. Min Range: -6.9793
Max Act: 6.7293. Min Act: -0.1700
Data Index: 4862927 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9793. Min Range: -6.9793
Max Act: 6.7605. Min Act: -0.1700
Data Index: 5743047 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9793. Min Range: -6.9793
Max Act: 6.6980. Min Act: -0.1700
Data Index: 3527260 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9793. Min Range: -6.9793
Max Act: 6.6980. Min Act: -0.1700
Data Index: 1742543 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9793. Min Range: -6.9793
Max Act: 6.6980. Min Act: -0.1700
Data Index: 176475 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9793. Min Range: -6.9793
Max Act: 6.6668. Min Act: -0.1700
Data Index: 2382742 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9793. Min Range: -6.9793
Max Act: 6.6668. Min Act: -0.1700
Data Index: 1576506 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9793. Min Range: -6.9793
Max Act: 6.6668. Min Act: -0.1700
Data Index: 1186474 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9793. Min Range: -6.9793
Max Act: 6.6668. Min Act: -0.1700
Data Index: 6037145 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9793. Min Range: -6.9793
Max Act: 6.6355. Min Act: -0.1700
Data Index: 3238966 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9793. Min Range: -6.9793
Max Act: 6.6043. Min Act: -0.1700
Data Index: 5266105 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9793. Min Range: -6.9793
Max Act: 6.6355. Min Act: -0.1700
Data Index: 3794266 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9793. Min Range: -6.9793
Max Act: 6.6043. Min Act: -0.1700
Data Index: 962362 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19