Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4302 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1806. Min Range: -7.1806
Max Act: 7.1806. Min Act: -0.1700
Data Index: 1765240 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1806. Min Range: -7.1806
Max Act: 7.1494. Min Act: -0.1700
Data Index: 4967268 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1806. Min Range: -7.1806
Max Act: 7.0556. Min Act: -0.1700
Data Index: 3185629 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1806. Min Range: -7.1806
Max Act: 7.0244. Min Act: -0.1700
Data Index: 1161949 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1806. Min Range: -7.1806
Max Act: 7.0244. Min Act: -0.1700
Data Index: 5777774 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1806. Min Range: -7.1806
Max Act: 6.9931. Min Act: -0.1700
Data Index: 1675562 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1806. Min Range: -7.1806
Max Act: 6.9931. Min Act: -0.1700
Data Index: 1197037 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1806. Min Range: -7.1806
Max Act: 6.8994. Min Act: -0.1700
Data Index: 4384682 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1806. Min Range: -7.1806
Max Act: 6.8994. Min Act: -0.1700
Data Index: 994971 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1806. Min Range: -7.1806
Max Act: 6.8994. Min Act: -0.1700
Data Index: 95770 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1806. Min Range: -7.1806
Max Act: 6.8681. Min Act: -0.1700
Data Index: 6543568 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1806. Min Range: -7.1806
Max Act: 6.8681. Min Act: -0.1700
Data Index: 7792888 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1806. Min Range: -7.1806
Max Act: 6.8681. Min Act: -0.1700
Data Index: 6002630 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1806. Min Range: -7.1806
Max Act: 6.8681. Min Act: -0.1700
Data Index: 8323025 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1806. Min Range: -7.1806
Max Act: 6.8369. Min Act: -0.1700
Data Index: 4643487 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1806. Min Range: -7.1806
Max Act: 6.8369. Min Act: -0.1700
Data Index: 5763331 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1806. Min Range: -7.1806
Max Act: 6.8369. Min Act: -0.1700
Data Index: 1221805 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1806. Min Range: -7.1806
Max Act: 6.8369. Min Act: -0.1700
Data Index: 1215431 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1806. Min Range: -7.1806
Max Act: 6.8056. Min Act: -0.1700
Data Index: 8151381 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1806. Min Range: -7.1806
Max Act: 6.8056. Min Act: -0.1700
Data Index: 5133723 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19