Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 947 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3277. Min Range: -5.3277
Max Act: 5.3277. Min Act: -0.1700
Data Index: 6802269 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3277. Min Range: -5.3277
Max Act: 5.2965. Min Act: -0.1700
Data Index: 1070553 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3277. Min Range: -5.3277
Max Act: 5.2965. Min Act: -0.1700
Data Index: 7671659 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3277. Min Range: -5.3277
Max Act: 5.2965. Min Act: -0.1700
Data Index: 4626826 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3277. Min Range: -5.3277
Max Act: 5.2652. Min Act: -0.1700
Data Index: 27983 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3277. Min Range: -5.3277
Max Act: 5.1402. Min Act: -0.1700
Data Index: 2039591 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3277. Min Range: -5.3277
Max Act: 5.0777. Min Act: -0.1700
Data Index: 5862703 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3277. Min Range: -5.3277
Max Act: 5.0777. Min Act: -0.1700
Data Index: 643755 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3277. Min Range: -5.3277
Max Act: 5.0465. Min Act: -0.1700
Data Index: 4383397 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3277. Min Range: -5.3277
Max Act: 5.0465. Min Act: -0.1700
Data Index: 7353323 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3277. Min Range: -5.3277
Max Act: 5.0465. Min Act: -0.1700
Data Index: 5056715 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3277. Min Range: -5.3277
Max Act: 5.0152. Min Act: -0.1700
Data Index: 7658172 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3277. Min Range: -5.3277
Max Act: 4.9840. Min Act: -0.1700
Data Index: 6064013 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3277. Min Range: -5.3277
Max Act: 4.9840. Min Act: -0.1700
Data Index: 6331670 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3277. Min Range: -5.3277
Max Act: 4.9527. Min Act: -0.1700
Data Index: 7253751 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3277. Min Range: -5.3277
Max Act: 4.9527. Min Act: -0.1700
Data Index: 2407751 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3277. Min Range: -5.3277
Max Act: 4.9527. Min Act: -0.1700
Data Index: 4583193 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3277. Min Range: -5.3277
Max Act: 4.9527. Min Act: -0.1700
Data Index: 5432532 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3277. Min Range: -5.3277
Max Act: 4.9527. Min Act: -0.1700
Data Index: 7229229 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3277. Min Range: -5.3277
Max Act: 4.9215. Min Act: -0.1700
Data Index: 5630185 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19