Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4090 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9101. Min Range: -4.9101
Max Act: 4.9101. Min Act: -0.1700
Data Index: 5914811 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9101. Min Range: -4.9101
Max Act: 4.8163. Min Act: -0.1700
Data Index: 1259742 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9101. Min Range: -4.9101
Max Act: 4.8163. Min Act: -0.1700
Data Index: 81160 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9101. Min Range: -4.9101
Max Act: 4.7538. Min Act: -0.1700
Data Index: 1423752 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9101. Min Range: -4.9101
Max Act: 4.6913. Min Act: -0.1700
Data Index: 7200543 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9101. Min Range: -4.9101
Max Act: 4.6913. Min Act: -0.1700
Data Index: 6919389 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9101. Min Range: -4.9101
Max Act: 4.6913. Min Act: -0.1700
Data Index: 4936176 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9101. Min Range: -4.9101
Max Act: 4.6601. Min Act: -0.1700
Data Index: 4871030 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9101. Min Range: -4.9101
Max Act: 4.6601. Min Act: -0.1700
Data Index: 2734506 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9101. Min Range: -4.9101
Max Act: 4.6288. Min Act: -0.1700
Data Index: 5035268 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9101. Min Range: -4.9101
Max Act: 4.6288. Min Act: -0.1700
Data Index: 4347970 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9101. Min Range: -4.9101
Max Act: 4.5976. Min Act: -0.1700
Data Index: 8471099 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9101. Min Range: -4.9101
Max Act: 4.5976. Min Act: -0.1700
Data Index: 1191625 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9101. Min Range: -4.9101
Max Act: 4.5976. Min Act: -0.1700
Data Index: 6142357 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9101. Min Range: -4.9101
Max Act: 4.5976. Min Act: -0.1700
Data Index: 1114226 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9101. Min Range: -4.9101
Max Act: 4.5663. Min Act: -0.1700
Data Index: 6352120 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9101. Min Range: -4.9101
Max Act: 4.5663. Min Act: -0.1700
Data Index: 5437141 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9101. Min Range: -4.9101
Max Act: 4.5351. Min Act: -0.1700
Data Index: 6705789 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9101. Min Range: -4.9101
Max Act: 4.5038. Min Act: -0.1700
Data Index: 5686867 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9101. Min Range: -4.9101
Max Act: 4.5663. Min Act: -0.1700
Data Index: 1082585 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19